Fix tests

* Fix off-thread RunStatus race where GetStatusAsync can return Running after ResumeAsync halts

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Simplify test comment.

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

.github/scripts/check_team_membership.js

@@ -0,0 +1,61 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Resolve the issue author and check their team membership.
+ *
+ * @param {object} opts
+ * @param {object} opts.github - Octokit REST client from actions/github-script
+ * @param {object} opts.context - GitHub Actions context
+ * @param {object} opts.core - GitHub Actions core toolkit
+ * @param {string} opts.teamSlug - Team slug to check membership against
+ * @param {string|number} opts.issueNumber - Issue number to resolve author for
+ * @returns {Promise<{author: string|null, isTeamMember: boolean}>}
+ */
+async function checkTeamMembership({ github, context, core, teamSlug, issueNumber }) {
+  let author = context.payload.issue?.user?.login;
+  if (!author) {
+    const { data: issue } = await github.rest.issues.get({
+      owner: context.repo.owner,
+      repo: context.repo.repo,
+      issue_number: Number(issueNumber),
+    });
+    author = issue.user?.login;
+  }
+
+  if (!author) {
+    core.setFailed('Could not determine issue author (user may be deleted).');
+    return { author: null, isTeamMember: false };
+  }
+
+  try {
+    await github.rest.teams.getByName({
+      org: context.repo.owner,
+      team_slug: teamSlug,
+    });
+  } catch (error) {
+    core.setFailed(`Team lookup failed for ${teamSlug}: ${error.message}`);
+    throw error;
+  }
+
+  let isTeamMember = false;
+  try {
+    const teamMembership = await github.rest.teams.getMembershipForUserInOrg({
+      org: context.repo.owner,
+      team_slug: teamSlug,
+      username: author,
+    });
+    isTeamMember = teamMembership.data.state === 'active';
+  } catch (error) {
+    if (error.status === 404) {
+      core.info(`Author ${author} is not a member of team ${teamSlug}.`);
+      isTeamMember = false;
+    } else {
+      core.setFailed(`Team membership lookup failed for ${author}: ${error.message}`);
+      throw error;
+    }
+  }
+
+  return { author, isTeamMember };
+}
+
+module.exports = checkTeamMembership;

.github/tests/test_check_team_membership.js

@@ -0,0 +1,178 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Tests for check_team_membership.js.
+ *
+ * Run with: node --test .github/tests/test_check_team_membership.js
+ */
+
+const { describe, it } = require('node:test');
+const assert = require('node:assert/strict');
+
+const checkTeamMembership = require('../scripts/check_team_membership.js');
+
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+function createMocks({ payloadIssue = undefined, apiUser = 'api-user', teamState = 'active' } = {}) {
+  const core = {
+    _infoMessages: [],
+    _failedMessages: [],
+    info(msg) { this._infoMessages.push(msg); },
+    setFailed(msg) { this._failedMessages.push(msg); },
+  };
+
+  const context = {
+    payload: { issue: payloadIssue },
+    repo: { owner: 'test-org', repo: 'test-repo' },
+  };
+
+  const github = {
+    rest: {
+      issues: {
+        get: async () => ({
+          data: { user: apiUser ? { login: apiUser } : null },
+        }),
+      },
+      teams: {
+        getByName: async () => ({}),
+        getMembershipForUserInOrg: async () => ({
+          data: { state: teamState },
+        }),
+      },
+    },
+  };
+
+  return { core, context, github };
+}
+
+const BASE_OPTS = { teamSlug: 'my-team', issueNumber: '123' };
+
+
+// ---------------------------------------------------------------------------
+// Author resolution
+// ---------------------------------------------------------------------------
+
+describe('author resolution', () => {
+  it('resolves author from event payload', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'payload-user' } },
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'payload-user');
+  });
+
+  it('resolves author via API when payload issue is absent', async () => {
+    const { github, context, core } = createMocks({ apiUser: 'api-user' });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'api-user');
+  });
+
+  it('resolves author via API when payload issue user is null (deleted account)', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: null },
+      apiUser: 'fetched-user',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'fetched-user');
+  });
+
+  it('handles deleted account when API also returns null user', async () => {
+    const { github, context, core } = createMocks({ apiUser: null });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, null);
+    assert.equal(result.isTeamMember, false);
+    assert.ok(core._failedMessages.some(m => m.includes('deleted')));
+  });
+});
+
+
+// ---------------------------------------------------------------------------
+// Team lookup
+// ---------------------------------------------------------------------------
+
+describe('team lookup', () => {
+  it('fails the job when team lookup errors', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const error = new Error('Bad credentials');
+    github.rest.teams.getByName = async () => { throw error; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === error,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('Team lookup failed')));
+  });
+});
+
+
+// ---------------------------------------------------------------------------
+// Team membership
+// ---------------------------------------------------------------------------
+
+describe('team membership', () => {
+  it('returns true for active team member', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'member' } },
+      teamState: 'active',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, true);
+  });
+
+  it('returns false for pending team member', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'pending-user' } },
+      teamState: 'pending',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, false);
+  });
+
+  it('treats 404 membership response as non-member without failing', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'outsider' } },
+    });
+    const notFoundError = new Error('Not Found');
+    notFoundError.status = 404;
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw notFoundError; };
+
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, false);
+    assert.equal(core._failedMessages.length, 0);
+    assert.ok(core._infoMessages.some(m => m.includes('not a member')));
+  });
+
+  it('fails the job on non-404 membership errors', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const serverError = new Error('Internal Server Error');
+    serverError.status = 500;
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw serverError; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === serverError,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('membership lookup failed')));
+  });
+
+  it('fails the job on membership errors without status code', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const networkError = new Error('ECONNREFUSED');
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw networkError; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === networkError,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('membership lookup failed')));
+  });
+});

.github/workflows/devflow-pr-review.yml

@@ -108,6 +108,10 @@ jobs:
     needs: team_check
     if: ${{ needs.team_check.outputs.is_team_member == 'true' }}
     timeout-minutes: 60
+    # Advisory check: failures here should not block the PR. The reviewer
+    # posts comments as a best-effort signal; if the pipeline breaks, the
+    # PR author should still be able to merge without a red required check.
+    continue-on-error: true
 
     steps:
       # Safe checkout: base repo only, not the untrusted PR head.

.github/workflows/issue-triage.yml

@@ -0,0 +1,199 @@
+name: Issue Triage
+
+on:
+  workflow_dispatch:
+    inputs:
+      issue_number:
+        description: Issue number to triage
+        required: true
+        type: string
+
+permissions:
+  contents: read
+  issues: write
+  id-token: write
+
+concurrency:
+  group: issue-triage-${{ github.repository }}-${{ github.event.issue.number || inputs.issue_number || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DEVFLOW_REPOSITORY: ${{ vars.DF_REPO }}
+  DEVFLOW_REF: main
+  TARGET_REPO_PATH: ${{ github.workspace }}/target-repo
+  DEVFLOW_PATH: ${{ github.workspace }}/devflow
+
+jobs:
+  team_check:
+    runs-on: ubuntu-latest
+    outputs:
+      is_team_member: ${{ steps.check.outputs.is_team_member }}
+      issue_number: ${{ steps.issue.outputs.issue_number }}
+      repo: ${{ steps.issue.outputs.repo }}
+    steps:
+      - name: Resolve issue metadata
+        id: issue
+        shell: bash
+        env:
+          ISSUE_NUMBER_EVENT: ${{ github.event.issue.number }}
+          ISSUE_NUMBER_INPUT: ${{ inputs.issue_number }}
+        run: |
+          set -euo pipefail
+
+          if [[ "${GITHUB_EVENT_NAME}" == "issues" ]]; then
+            issue_number="${ISSUE_NUMBER_EVENT}"
+          else
+            issue_number="${ISSUE_NUMBER_INPUT}"
+          fi
+
+          if [[ ! "$issue_number" =~ ^[1-9][0-9]*$ ]]; then
+            echo "Could not determine issue number; for workflow_dispatch runs, the 'issue_number' input is required." >&2
+            exit 1
+          fi
+
+          echo "issue_number=${issue_number}" >> "$GITHUB_OUTPUT"
+          echo "repo=${GITHUB_REPOSITORY}" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout scripts
+        uses: actions/checkout@v6
+        with:
+          sparse-checkout: .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Check issue author team membership
+        id: check
+        uses: actions/github-script@v8
+        env:
+          TEAM_NAME: ${{ secrets.DEVELOPER_TEAM }}
+          ISSUE_NUMBER: ${{ steps.issue.outputs.issue_number }}
+        with:
+          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+          script: |
+            const checkTeamMembership = require('./.github/scripts/check_team_membership.js');
+            const { author, isTeamMember } = await checkTeamMembership({
+              github,
+              context,
+              core,
+              teamSlug: process.env.TEAM_NAME,
+              issueNumber: process.env.ISSUE_NUMBER,
+            });
+            core.setOutput('is_team_member', isTeamMember ? 'true' : 'false');
+            if (isTeamMember) {
+              core.info(`Author ${author} is a team member; skipping auto-triage.`);
+            } else {
+              core.info(`Author ${author} is not a team member; proceeding with triage.`);
+            }
+
+  triage:
+    runs-on: ubuntu-latest
+    needs: team_check
+    if: ${{ needs.team_check.outputs.is_team_member == 'false' }}
+    environment: integration
+    timeout-minutes: 60
+
+    steps:
+      # Safe checkout: base repo only.
+      - name: Checkout target repo base
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+          path: target-repo
+
+      # Private DevFlow (maf-dashboard) checkout.
+      - name: Checkout DevFlow
+        uses: actions/checkout@v6
+        with:
+          repository: ${{ env.DEVFLOW_REPOSITORY }}
+          ref: ${{ env.DEVFLOW_REF }}
+          token: ${{ secrets.DEVFLOW_TOKEN }}
+          fetch-depth: 1
+          persist-credentials: false
+          path: devflow
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "0.11.x"
+          enable-cache: true
+
+      - name: Install DevFlow dependencies
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        run: uv sync --frozen
+
+      - name: Azure CLI Login
+        uses: azure/login@v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+
+      - name: Classify issue relevance
+        id: spam
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          SK_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          AGENT_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          ISSUE_REPO: ${{ needs.team_check.outputs.repo }}
+          ISSUE_NUMBER: ${{ needs.team_check.outputs.issue_number }}
+        run: |
+          uv run python scripts/classify_issue_spam.py \
+            --repo "$ISSUE_REPO" \
+            --issue-number "$ISSUE_NUMBER" \
+            --repo-path "${TARGET_REPO_PATH}" \
+            --apply-labels
+
+      - name: Stop after spam gate
+        if: ${{ steps.spam.outputs.decision != 'allow' }}
+        shell: bash
+        env:
+          SPAM_DECISION: ${{ steps.spam.outputs.decision }}
+        run: |
+          echo "Stopping: spam gate decided: ${SPAM_DECISION}"
+          exit 1
+
+      - name: Reproduce reported issue
+        if: ${{ steps.spam.outputs.decision == 'allow' }}
+        id: repro
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_COPILOT_TOKEN: ${{ secrets.GH_COPILOT_TOKEN }}
+          SK_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          AGENT_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          ISSUE_REPO: ${{ needs.team_check.outputs.repo }}
+          ISSUE_NUMBER: ${{ needs.team_check.outputs.issue_number }}
+          # Model-provider settings for generated repro code. Never enter the
+          # agent prompt; consumed by SDK constructors via os.environ. Azure
+          # OpenAI and Foundry auth via AAD from the azure/login step above.
+          OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
+          OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.OPENAI__CHATMODELID }}
+          OPENAI_CHAT_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
+          OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
+          OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
+          AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
+          AZURE_OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
+          AZURE_OPENAI_CHAT_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+          AZURE_OPENAI_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+          AZURE_OPENAI_EMBEDDING_MODEL: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
+          FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
+          FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
+          FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
+          FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
+          FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
+          FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
+          FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
+        run: |
+          uv run python scripts/trigger_issue_repro.py \
+            --repo "$ISSUE_REPO" \
+            --issue-number "$ISSUE_NUMBER" \
+            --github-username "$GITHUB_ACTOR"

.github/workflows/python-integration-tests.yml

@@ -87,6 +87,14 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure OpenAI integration tests
   python-tests-azure-openai:
@@ -130,6 +138,14 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-azure-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Misc integration tests (Anthropic, Hyperlight, Ollama, MCP)
   python-tests-misc-integration:
@@ -173,6 +189,14 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 30
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-misc
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
       - name: Stop local MCP server
         if: always()
         shell: bash
@@ -249,6 +273,14 @@ jobs:
           -x
           --timeout=360 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-functions
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Foundry integration tests
   python-tests-foundry:
@@ -295,6 +327,14 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-foundry
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure Cosmos integration tests
   python-tests-cosmos:
@@ -339,7 +379,80 @@ jobs:
           echo "Cosmos DB emulator did not become ready in time." >&2
           exit 1
       - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos 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-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-cosmos
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Flaky test trend report (aggregates per-job JUnit XML results)
+  python-flaky-test-report:
+    name: Flaky Test Report
+    if: >
+      always() &&
+      (contains(join(needs.*.result, ','), 'success') ||
+       contains(join(needs.*.result, ','), 'failure'))
+    needs:
+      [
+        python-tests-openai,
+        python-tests-azure-openai,
+        python-tests-misc-integration,
+        python-tests-functions,
+        python-tests-foundry,
+        python-tests-cosmos,
+      ]
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          ref: ${{ inputs.checkout-ref }}
+          persist-credentials: false
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Download all test results from current run
+        uses: actions/download-artifact@v4
+        with:
+          pattern: test-results-*
+          path: test-results/
+      - name: Restore flaky report history cache
+        uses: actions/cache/restore@v4
+        with:
+          path: python/flaky-report-history.json
+          key: flaky-report-history-integration-${{ github.run_id }}
+          restore-keys: |
+            flaky-report-history-integration-
+      - name: Generate trend report
+        run: >
+          uv run python scripts/flaky_report/aggregate.py
+          ../test-results/
+          flaky-report-history.json
+          flaky-test-report.md
+      - name: Post to Job Summary
+        if: always()
+        run: cat flaky-test-report.md >> $GITHUB_STEP_SUMMARY
+      - name: Save flaky report history cache
+        if: always()
+        uses: actions/cache/save@v4
+        with:
+          path: python/flaky-report-history.json
+          key: flaky-report-history-integration-${{ github.run_id }}
+      - name: Upload unified trend report
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: flaky-test-report
+          path: |
+            python/flaky-test-report.md
+            python/flaky-report-history.json
 
   python-integration-tests-check:
     if: always()

.github/workflows/python-merge-tests.yml

@@ -181,6 +181,13 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: OpenAI integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure OpenAI integration tests
   python-tests-azure-openai:
@@ -244,6 +251,13 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: Azure OpenAI integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-azure-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Misc integration tests (Anthropic, Ollama, MCP)
   python-tests-misc-integration:
@@ -321,6 +335,13 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: Misc integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-misc
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure Functions + Durable Task integration tests
   python-tests-functions:
@@ -392,6 +413,13 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: Functions integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-functions
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   python-tests-foundry:
     name: Python Integration Tests - Foundry
@@ -409,6 +437,10 @@ jobs:
       FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
       FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
       FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
+      FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
+      FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
+      FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
+      FOUNDRY_IMAGE_EMBEDDING_MODEL: ${{ vars.FOUNDRY_IMAGE_EMBEDDING_MODEL || '' }}
       LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
     defaults:
       run:
@@ -448,6 +480,13 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: Test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-foundry
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # TODO: Add python-tests-lab
 
@@ -497,7 +536,7 @@ jobs:
           echo "Cosmos DB emulator did not become ready in time." >&2
           exit 1
       - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=pytest.xml
+        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
         working-directory: ./python
       - name: Surface failing tests
         if: always()
@@ -508,6 +547,76 @@ jobs:
           display-options: fEX
           fail-on-empty: false
           title: Cosmos integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: test-results-cosmos
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Flaky test trend report (aggregates per-job JUnit XML results)
+  python-flaky-test-report:
+    name: Flaky Test Report
+    if: >
+      always() &&
+      (contains(join(needs.*.result, ','), 'success') ||
+       contains(join(needs.*.result, ','), 'failure'))
+    needs:
+      [
+        python-tests-openai,
+        python-tests-azure-openai,
+        python-tests-misc-integration,
+        python-tests-functions,
+        python-tests-foundry,
+        python-tests-cosmos,
+      ]
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@v6
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Download all test results from current run
+        uses: actions/download-artifact@v4
+        with:
+          pattern: test-results-*
+          path: test-results/
+      - name: Restore flaky report history cache
+        uses: actions/cache/restore@v4
+        with:
+          path: python/flaky-report-history.json
+          key: flaky-report-history-merge-${{ github.run_id }}
+          restore-keys: |
+            flaky-report-history-merge-
+      - name: Generate trend report
+        run: >
+          uv run python scripts/flaky_report/aggregate.py
+          ../test-results/
+          flaky-report-history.json
+          flaky-test-report.md
+      - name: Post to Job Summary
+        if: always()
+        run: cat flaky-test-report.md >> $GITHUB_STEP_SUMMARY
+      - name: Save flaky report history cache
+        if: always()
+        uses: actions/cache/save@v4
+        with:
+          path: python/flaky-report-history.json
+          key: flaky-report-history-merge-${{ github.run_id }}
+      - name: Upload unified trend report
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: flaky-test-report
+          path: |
+            python/flaky-test-report.md
+            python/flaky-report-history.json
 
   python-integration-tests-check:
     if: always()

dotnet/agent-framework-dotnet.slnx

@@ -4,9 +4,6 @@
     <BuildType Name="Publish" />
     <BuildType Name="Release" />
   </Configurations>
-  <Folder Name="/src/Aspire.Hosting.AgentFramework.DevUI/">
-    <Project Path="src/Aspire.Hosting.AgentFramework.DevUI/Aspire.Hosting.AgentFramework.DevUI.csproj" />
-  </Folder>
   <Folder Name="/Samples/">
     <File Path="samples/AGENTS.md" />
     <File Path="samples/README.md" />
@@ -67,6 +64,7 @@
     <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" />
+    <Project Path="samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Agent_Step20_DynamicFunctionTools.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/DeclarativeAgents/">
     <Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
@@ -533,6 +531,7 @@
     <File Path="tests/Directory.Build.props" />
   </Folder>
   <Folder Name="/src/">
+    <Project Path="src/Aspire.Hosting.AgentFramework.DevUI/Aspire.Hosting.AgentFramework.DevUI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.A2A/Microsoft.Agents.AI.A2A.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Abstractions/Microsoft.Agents.AI.Abstractions.csproj" />
     <Project Path="src/Microsoft.Agents.AI.AGUI/Microsoft.Agents.AI.AGUI.csproj" />

dotnet/samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Agent_Step20_DynamicFunctionTools.csproj

@@ -0,0 +1,20 @@
+<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>

dotnet/samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Program.cs

@@ -0,0 +1,281 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates how to dynamically expand the set of function tools available to an
+// agent during a function-calling loop. The agent starts with a single "RequestTools" function.
+// When the model calls RequestTools with a description of the capabilities needed, the function
+// uses the ambient FunctionInvocationContext to add new tools to ChatOptions.Tools. The agent
+// can then use the newly added tools in subsequent iterations of the same function-calling loop.
+
+using System.ComponentModel;
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+using Microsoft.Extensions.AI;
+
+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-5.4-mini";
+
+// Pre-defined tool implementations that can be loaded on demand.
+[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.",
+        _ => $"{city}: weather data not available, please provide one of the following city names: 'Seattle', 'New York', 'London'."
+    };
+
+[Description("Get the current local time for 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",
+        _ => $"{city}: time data not available, please provide one of the following city names: 'Seattle', 'New York', 'London'."
+    };
+
+[Description("Convert a temperature from Fahrenheit to Celsius.")]
+static string ConvertFahrenheitToCelsius([Description("The temperature in Fahrenheit.")] double fahrenheit) =>
+    $"{fahrenheit}°F = {(fahrenheit - 32) * 5 / 9:F1}°C";
+
+// A registry of tool sets that can be loaded by description keyword.
+Dictionary<string, List<AITool>> toolCatalog = new(StringComparer.OrdinalIgnoreCase)
+{
+    ["weather"] = [AIFunctionFactory.Create(GetWeather, name: "GetWeather")],
+    ["time"] = [AIFunctionFactory.Create(GetTime, name: "GetTime")],
+    ["temperature"] = [AIFunctionFactory.Create(ConvertFahrenheitToCelsius, name: "ConvertFahrenheitToCelsius")],
+};
+
+// The RequestTools function uses the ambient FunctionInvocationContext to add tools dynamically.
+AIFunction requestToolsFunction = AIFunctionFactory.Create(
+    [Description("Request additional tools to be loaded based on a description of the functionality needed. " +
+                 "Call this when you need capabilities that are not yet available in your current tool set.")] (
+        [Description("A description of the functionality required, e.g. 'weather', 'time', or 'temperature conversion'.")] string description
+    ) =>
+    {
+        // Access the ambient FunctionInvocationContext provided by FunctionInvokingChatClient.
+        var context = FunctionInvokingChatClient.CurrentContext
+            ?? throw new InvalidOperationException("No ambient FunctionInvocationContext available.");
+
+        var tools = context.Options?.Tools;
+        if (tools is null)
+        {
+            return "Unable to register new tools: ChatOptions.Tools is not available.";
+        }
+
+        // Find matching tool sets from the catalog.
+        List<string> addedToolNames = [];
+        foreach (var kvp in toolCatalog)
+        {
+            var keyword = kvp.Key;
+            var catalogTools = kvp.Value;
+            if (description.Contains(keyword, StringComparison.OrdinalIgnoreCase))
+            {
+                foreach (var tool in catalogTools)
+                {
+                    // Avoid adding duplicates.
+                    if (tool is AIFunction fn && !tools.Any(t => t is AIFunction existing && existing.Name == fn.Name))
+                    {
+                        tools.Add(tool);
+                        addedToolNames.Add(fn.Name);
+                    }
+                }
+            }
+        }
+
+        return addedToolNames.Count > 0
+            ? "Successfully loaded tools"
+            : $"No tools matched the description '{description}'. Available categories: {string.Join(", ", toolCatalog.Keys)}.";
+    },
+    name: "RequestTools");
+
+// Create the agent with only the RequestTools function initially.
+// Insert chat client middleware that logs the tools available on each LLM call,
+// making the dynamic expansion visible in the console output.
+// 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.
+AIAgent agent = new AzureOpenAIClient(
+    new Uri(endpoint),
+    new DefaultAzureCredential())
+    .GetChatClient(deploymentName)
+    .AsIChatClient()
+    .AsBuilder()
+    .Use(getResponseFunc: ToolLoggingMiddleware, getStreamingResponseFunc: ToolLoggingStreamingMiddleware)
+    .BuildAIAgent(
+        instructions: """
+            You are a helpful assistant. You start with limited tools.
+            When you need functionality that you don't currently have, call RequestTools with a description
+            of what you need. After new tools are loaded, use them to answer the user's question.
+            """,
+        tools: [requestToolsFunction]);
+
+// Run a conversation that triggers dynamic tool expansion.
+Console.WriteLine("=== Dynamic Function Tools Sample ===\n");
+
+string[] prompts =
+[
+    "What's the weather like in Seattle and London?",
+    "What time is it in New York?",
+    "Can you convert those temperatures to Celsius?"
+];
+
+// --- Non-Streaming Mode ---
+Console.ForegroundColor = ConsoleColor.Yellow;
+Console.WriteLine("=== Non-Streaming Mode ===");
+Console.ResetColor();
+Console.WriteLine();
+
+AgentSession session = await agent.CreateSessionAsync();
+
+foreach (var prompt in prompts)
+{
+    Console.ForegroundColor = ConsoleColor.Green;
+    Console.Write("[User] ");
+    Console.ResetColor();
+    Console.WriteLine(prompt);
+
+    var response = await agent.RunAsync(prompt, session);
+
+    // Print all message contents including tool calls, tool results, and text.
+    foreach (var message in response.Messages)
+    {
+        foreach (var content in message.Contents)
+        {
+            switch (content)
+            {
+                case FunctionCallContent functionCall:
+                    Console.ForegroundColor = ConsoleColor.Yellow;
+                    Console.WriteLine($"  [Tool Call] {functionCall.Name}({string.Join(", ", functionCall.Arguments?.Select(a => $"{a.Key}: {a.Value}") ?? [])})");
+                    Console.ResetColor();
+                    break;
+
+                case FunctionResultContent functionResult:
+                    Console.ForegroundColor = ConsoleColor.DarkYellow;
+                    Console.WriteLine($"  [Tool Result] {functionResult.CallId} => {functionResult.Result}");
+                    Console.ResetColor();
+                    break;
+
+                case TextContent textContent when !string.IsNullOrWhiteSpace(textContent.Text):
+                    Console.ForegroundColor = ConsoleColor.Cyan;
+                    Console.Write("[Agent] ");
+                    Console.ResetColor();
+                    Console.WriteLine(textContent.Text);
+                    break;
+            }
+        }
+    }
+
+    Console.WriteLine();
+}
+
+// --- Streaming Mode ---
+Console.ForegroundColor = ConsoleColor.Yellow;
+Console.WriteLine("=== Streaming Mode ===");
+Console.ResetColor();
+Console.WriteLine();
+
+AgentSession streamingSession = await agent.CreateSessionAsync();
+
+foreach (var prompt in prompts)
+{
+    Console.ForegroundColor = ConsoleColor.Green;
+    Console.Write("[User] ");
+    Console.ResetColor();
+    Console.WriteLine(prompt);
+
+    bool inAgentText = false;
+
+    await foreach (var update in agent.RunStreamingAsync(prompt, streamingSession))
+    {
+        foreach (var content in update.Contents)
+        {
+            switch (content)
+            {
+                case FunctionCallContent functionCall:
+                    if (inAgentText)
+                    {
+                        Console.WriteLine();
+                        inAgentText = false;
+                    }
+
+                    Console.ForegroundColor = ConsoleColor.Yellow;
+                    Console.WriteLine($"  [Tool Call] {functionCall.Name}({string.Join(", ", functionCall.Arguments?.Select(a => $"{a.Key}: {a.Value}") ?? [])})");
+                    Console.ResetColor();
+                    break;
+
+                case FunctionResultContent functionResult:
+                    Console.ForegroundColor = ConsoleColor.DarkYellow;
+                    Console.WriteLine($"  [Tool Result] {functionResult.CallId} => {functionResult.Result}");
+                    Console.ResetColor();
+                    break;
+
+                case TextContent textContent when !string.IsNullOrWhiteSpace(textContent.Text):
+                    if (!inAgentText)
+                    {
+                        Console.ForegroundColor = ConsoleColor.Cyan;
+                        Console.Write("[Agent] ");
+                        Console.ResetColor();
+                        inAgentText = true;
+                    }
+
+                    Console.Write(textContent.Text);
+                    break;
+            }
+        }
+    }
+
+    if (inAgentText)
+    {
+        Console.WriteLine();
+    }
+
+    Console.WriteLine();
+}
+
+// Chat client middleware that logs the number and names of tools on each LLM request.
+async Task<ChatResponse> ToolLoggingMiddleware(
+    IEnumerable<ChatMessage> messages,
+    ChatOptions? options,
+    IChatClient innerChatClient,
+    CancellationToken cancellationToken)
+{
+    LogTools(options);
+
+    return await innerChatClient.GetResponseAsync(messages, options, cancellationToken);
+}
+
+// Streaming version of the tool logging middleware.
+async IAsyncEnumerable<ChatResponseUpdate> ToolLoggingStreamingMiddleware(
+    IEnumerable<ChatMessage> messages,
+    ChatOptions? options,
+    IChatClient innerChatClient,
+    [System.Runtime.CompilerServices.EnumeratorCancellation] CancellationToken cancellationToken)
+{
+    LogTools(options);
+
+    await foreach (var update in innerChatClient.GetStreamingResponseAsync(messages, options, cancellationToken))
+    {
+        yield return update;
+    }
+}
+
+// Shared helper to log the current tool set.
+void LogTools(ChatOptions? options)
+{
+    if (options?.Tools is { Count: > 0 } tools)
+    {
+        var toolNames = tools.OfType<AIFunction>().Select(t => t.Name);
+        Console.ForegroundColor = ConsoleColor.DarkGray;
+        Console.WriteLine($"  [Middleware] LLM call with {tools.Count} tool(s): {string.Join(", ", toolNames)}");
+        Console.ResetColor();
+    }
+    else
+    {
+        Console.ForegroundColor = ConsoleColor.DarkGray;
+        Console.WriteLine("  [Middleware] LLM call with 0 tools");
+        Console.ResetColor();
+    }
+}

dotnet/samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/README.md

@@ -0,0 +1,38 @@
+# Dynamic Function Tools
+
+This sample demonstrates how to dynamically expand the set of function tools available to an agent during a function-calling loop.
+
+## What it demonstrates
+
+- The agent starts with only a single `RequestTools` function
+- When the model needs capabilities it doesn't have, it calls `RequestTools` with a description of the functionality needed
+- The `RequestTools` function uses the ambient `FunctionInvokingChatClient.CurrentContext` to access `ChatOptions.Tools` and add new tools at runtime
+- The agent then uses the newly added tools in subsequent iterations of the same function-calling loop
+
+## How it works
+
+1. A tool catalog maps keywords (e.g. "weather", "time", "temperature") to pre-built `AIFunction` instances
+2. The `RequestTools` function matches the description against catalog keywords and adds matching tools to `ChatOptions.Tools`
+3. `FunctionInvokingChatClient` automatically picks up the new tools on the next iteration of its loop
+
+## Prerequisites
+
+- .NET 10 SDK or later
+- Azure OpenAI service endpoint and deployment configured
+- Azure CLI installed and authenticated (for Azure credential authentication)
+- User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource
+
+## Running the sample
+
+Set the required environment variables:
+
+```powershell
+$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
+$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini"  # Optional, defaults to gpt-5.4-mini
+```
+
+Run the sample:
+
+```powershell
+dotnet run
+```

dotnet/samples/02-agents/Agents/README.md

@@ -46,6 +46,7 @@ Before you begin, ensure you have the following prerequisites:
 |[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.|
+|[Dynamic function tools](./Agent_Step20_DynamicFunctionTools/)|This sample demonstrates how to dynamically expand the set of function tools available to an agent during a function-calling loop using the ambient FunctionInvocationContext.|
 
 ## Running the samples from the console
 

dotnet/src/Aspire.Hosting.AgentFramework.DevUI/Aspire.Hosting.AgentFramework.DevUI.csproj

@@ -2,14 +2,22 @@
 
   <PropertyGroup>
     <TargetFrameworks>$(TargetFrameworksCore)</TargetFrameworks>
-    <IsPackable>true</IsPackable>
-    <PackageTags>aspire integration hosting agent-framework devui ai agents</PackageTags>
-    <Description>Microsoft Agent Framework DevUI support for Aspire.</Description>
+    <VersionSuffix>preview</VersionSuffix>
     <!-- Suppress analyzer warnings for Aspire integration code -->
     <!-- IL2026/IL3050: Suppress trimming/AOT warnings - DevUI is a dev-only tool not intended for AOT -->
     <NoWarn>$(NoWarn);CA1873;RCS1061;VSTHRD002;IL2026;IL3050</NoWarn>
   </PropertyGroup>
 
+  <Import Project="$(RepoRoot)/dotnet/nuget/nuget-package.props" />
+
+  <PropertyGroup>
+    <!-- NuGet Package Settings -->
+    <Title>Microsoft Agent Framework DevUI for Aspire</Title>
+    <PackageTags>aspire integration hosting agent-framework devui ai agents</PackageTags>
+    <Description>Microsoft Agent Framework DevUI support for Aspire.</Description>
+    <PackageReadmeFile>README.md</PackageReadmeFile>
+  </PropertyGroup>
+
   <ItemGroup>
     <InternalsVisibleTo Include="Aspire.Hosting.AgentFramework.DevUI.UnitTests" />
   </ItemGroup>
@@ -22,4 +30,7 @@
     <PackageReference Include="Aspire.Hosting" />
   </ItemGroup>
 
+  <ItemGroup>
+    <None Include="README.md" Pack="true" PackagePath="/" />
+  </ItemGroup>
 </Project>

dotnet/src/Microsoft.Agents.AI.Workflows/Execution/StreamingRunEventStream.cs

@@ -77,12 +77,13 @@ internal sealed class StreamingRunEventStream : IRunEventStream
 
         try
         {
-            // Wait for the first input before starting
-            // The consumer will call EnqueueMessageAsync which signals the run loop
+            // Wait for the first input before starting.
+            // The consumer will call EnqueueMessageAsync which signals the run loop.
+            // Note: AsyncRunHandle also signals here on checkpoint resume when there are
+            // already pending requests, so the first iteration can emit a PendingRequests
+            // halt signal even without unprocessed messages.
             await this._inputWaiter.WaitForInputAsync(cancellationToken: linkedSource.Token).ConfigureAwait(false);
 
-            this._runStatus = RunStatus.Running;
-
             while (!linkedSource.Token.IsCancellationRequested)
             {
                 // Start a new run-stage activity for this input→processing→halt cycle
@@ -95,6 +96,13 @@ internal sealed class StreamingRunEventStream : IRunEventStream
                 // Events are streamed out in real-time as they happen via the event handler
                 if (this._stepRunner.HasUnprocessedMessages)
                 {
+                    // Flip to Running only when there's actual work to process.
+                    // This is intentionally inside the HasUnprocessedMessages branch so
+                    // that stale input signals cannot transiently flip status back to
+                    // Running after a prior halt has already been observed by callers
+                    // (e.g. Run.ResumeAsync returning after reading an Idle halt signal).
+                    this._runStatus = RunStatus.Running;
+
                     // Emit WorkflowStartedEvent only when there's actual work to process
                     // This avoids spurious events on timeout-only loop iterations
                     await this._eventChannel.Writer.WriteAsync(new WorkflowStartedEvent(), linkedSource.Token).ConfigureAwait(false);
@@ -129,9 +137,6 @@ internal sealed class StreamingRunEventStream : IRunEventStream
                 // Wait for next input from the consumer
                 // Works for both Idle (no work) and PendingRequests (waiting for responses)
                 await this._inputWaiter.WaitForInputAsync(linkedSource.Token).ConfigureAwait(false);
-
-                // When signaled, resume running
-                this._runStatus = RunStatus.Running;
             }
         }
         catch (OperationCanceledException)

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/SampleSmokeTest.cs

@@ -269,6 +269,29 @@ public class SampleSmokeTest
         _ = await Step9EntryPoint.RunAsync(writer, environment.ToWorkflowExecutionEnvironment());
     }
 
+    /// <summary>
+    /// Stress regression for the off-thread run-status race: after
+    /// <c>Run.ResumeAsync</c> returns at a halt boundary,
+    /// callers must observe a stable terminal status and never a transient
+    /// <see cref="RunStatus.Running"/>. Step9 is the canonical multi-response resume
+    /// sample; prior to the fix in <see cref="Execution.StreamingRunEventStream"/>,
+    /// its `runStatus.Should().Be(RunStatus.Idle)` assertion failed intermittently
+    /// on roughly 1-in-10 iterations under InProcess_OffThread.
+    /// </summary>
+    [Fact]
+    internal async Task Test_RunSample_Step9_OffThread_MultiResponseResume_StatusIsStableAsync()
+    {
+        const int Iterations = 50;
+
+        for (int i = 0; i < Iterations; i++)
+        {
+            using StringWriter writer = new();
+            _ = await Step9EntryPoint.RunAsync(
+                writer,
+                ExecutionEnvironment.InProcess_OffThread.ToWorkflowExecutionEnvironment());
+        }
+    }
+
     [Theory]
     [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
     [InlineData(ExecutionEnvironment.InProcess_OffThread)]

python/CHANGELOG.md

@@ -7,6 +7,28 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.1.1] - 2026-04-23
+
+### Added
+- **agent-framework-core**: Add `expected_output` ground-truth support to `evaluate_workflow` for similarity evaluators ([#5234](https://github.com/microsoft/agent-framework/pull/5234))
+- **agent-framework-ag-ui**, **agent-framework-a2a**: Propagate `thread_id` and `forwarded_props` through AG-UI to A2A `context_id` ([#5383](https://github.com/microsoft/agent-framework/pull/5383))
+- **samples**: Add second approval-required tool (`set_stop_loss`) to `concurrent_builder_tool_approval` sample ([#4875](https://github.com/microsoft/agent-framework/pull/4875))
+- **agent-framework-core**: Add `SKIP_PARSING` sentinel for `FunctionTool.invoke` to bypass `Content`-wrapping and return raw function results ([#5424](https://github.com/microsoft/agent-framework/pull/5424))
+
+### Changed
+- **agent-framework-foundry-hosting**: Correct Development Status classifier from Beta (4) to Alpha (3) to match the package's lifecycle stage ([#5387](https://github.com/microsoft/agent-framework/pull/5387))
+- **tests**: Add Python flaky test report workflow ([#5342](https://github.com/microsoft/agent-framework/pull/5342))
+- **agent-framework-hyperlight**: Simplify host callback to pass raw Python results via `SKIP_PARSING`, switch `execute_code` input schema to a plain JSON-schema dict, and tighten public API surface ([#5424](https://github.com/microsoft/agent-framework/pull/5424))
+
+### Fixed
+- **agent-framework-openai**: Fix OpenAI Responses streaming to propagate `created_at` from the final `response.completed` event ([#5382](https://github.com/microsoft/agent-framework/pull/5382))
+- **agent-framework-openai**: Fix `OpenAIEmbeddingClient` to use `AsyncOpenAI` for `/openai/v1` endpoints ([#5137](https://github.com/microsoft/agent-framework/pull/5137))
+- **agent-framework-openai**: Exclude null `file_id` from `input_image` payload to prevent schema 400 errors ([#5125](https://github.com/microsoft/agent-framework/pull/5125))
+- **agent-framework-foundry**: Reconcile Toolbox hosted-tool payloads with the Responses API ([#5414](https://github.com/microsoft/agent-framework/pull/5414))
+- **agent-framework-ag-ui**: Pass client `thread_id` as `session_id` when constructing `AgentSession` ([#5384](https://github.com/microsoft/agent-framework/pull/5384))
+- **agent-framework-hyperlight**: Thread-confine `WasmSandbox` interactions via per-entry `ThreadPoolExecutor` to eliminate the PyO3 `unsendable` panic when touched from asyncio worker threads
+  ([#5424](https://github.com/microsoft/agent-framework/pull/5424))
+
 ## [1.1.0] - 2026-04-21
 
 ### Added

python/packages/a2a/agent_framework_a2a/_agent.py

@@ -295,7 +295,10 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
         else:
             if not normalized_messages:
                 raise ValueError("At least one message is required when starting a new task (no continuation_token).")
-            a2a_message = self._prepare_message_for_a2a(normalized_messages[-1])
+            a2a_message = self._prepare_message_for_a2a(
+                normalized_messages[-1],
+                context_id=session.service_session_id if session else None,
+            )
             a2a_stream = self.client.send_message(a2a_message)
 
         provider_session = session
@@ -584,7 +587,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
             return AgentResponse.from_updates(updates)
         return AgentResponse(messages=[], response_id=task.id, raw_representation=task)
 
-    def _prepare_message_for_a2a(self, message: Message) -> A2AMessage:
+    def _prepare_message_for_a2a(self, message: Message, *, context_id: str | None = None) -> A2AMessage:
         """Prepare a Message for the A2A protocol.
 
         Transforms Agent Framework Message objects into A2A protocol Messages by:
@@ -593,6 +596,13 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
         - Converting file references (URI/data/hosted_file) to FilePart objects
         - Preserving metadata and additional properties from the original message
         - Setting the role to 'user' as framework messages are treated as user input
+
+        Args:
+            message: The framework Message to convert.
+            context_id: Optional fallback context identifier (e.g. derived from
+                ``AgentSession.service_session_id``). When the *message* already
+                carries a ``context_id`` in its ``additional_properties`` that
+                value takes precedence; otherwise this fallback is used.
         """
         parts: list[A2APart] = []
         if not message.contents:
@@ -672,7 +682,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
             role=A2ARole("user"),
             parts=parts,
             message_id=message.message_id or uuid.uuid4().hex,
-            context_id=message.additional_properties.get("context_id"),
+            context_id=message.additional_properties.get("context_id") or context_id,
             metadata=metadata,
         )
 

python/packages/a2a/pyproject.toml

@@ -4,7 +4,7 @@ description = "A2A integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "a2a-sdk>=0.3.5,<0.3.24",
 ]
 

python/packages/a2a/tests/test_a2a_agent.py

@@ -46,6 +46,7 @@ class MockA2AClient:
         self.responses: list[Any] = []
         self.resubscribe_responses: list[Any] = []
         self.get_task_response: Task | None = None
+        self.last_message: Any = None
 
     def add_message_response(self, message_id: str, text: str, role: str = "agent") -> None:
         """Add a mock Message response."""
@@ -111,6 +112,7 @@ class MockA2AClient:
 
     async def send_message(self, message: Any) -> AsyncIterator[Any]:
         """Mock send_message method that yields responses."""
+        self.last_message = message
         self.call_count += 1
 
         # All queued responses are delivered as a single streaming batch per call.
@@ -539,6 +541,37 @@ def test_prepare_message_for_a2a_forwards_context_id() -> None:
     assert result.metadata == {"trace_id": "trace-456"}
 
 
+def test_prepare_message_for_a2a_uses_fallback_context_id() -> None:
+    """Test that context_id kwarg is used when message has no context_id property."""
+
+    agent = A2AAgent(client=MagicMock(), http_client=None)
+
+    message = Message(
+        role="user",
+        contents=[Content.from_text(text="Hello")],
+    )
+
+    result = agent._prepare_message_for_a2a(message, context_id="session-ctx-1")
+
+    assert result.context_id == "session-ctx-1"
+
+
+def test_prepare_message_for_a2a_message_context_id_takes_precedence() -> None:
+    """Test that message.additional_properties context_id wins over the fallback."""
+
+    agent = A2AAgent(client=MagicMock(), http_client=None)
+
+    message = Message(
+        role="user",
+        contents=[Content.from_text(text="Hello")],
+        additional_properties={"context_id": "explicit-ctx"},
+    )
+
+    result = agent._prepare_message_for_a2a(message, context_id="session-ctx-1")
+
+    assert result.context_id == "explicit-ctx"
+
+
 def test_parse_contents_from_a2a_with_data_part() -> None:
     """Test conversion of A2A DataPart."""
 
@@ -868,6 +901,43 @@ async def test_poll_task_completed(a2a_agent: A2AAgent, mock_a2a_client: MockA2A
 # endregion
 
 
+# region Session context_id Integration Tests
+
+
+@mark.asyncio
+async def test_run_passes_session_service_session_id_as_context_id(mock_a2a_client: MockA2AClient) -> None:
+    """Test that run() wires session.service_session_id to the A2A message context_id."""
+    agent = A2AAgent(name="Test Agent", id="test-agent", client=mock_a2a_client, http_client=None)
+    mock_a2a_client.add_message_response("msg-ctx", "reply")
+
+    session = AgentSession(service_session_id="svc-session-42")
+    await agent.run("Hello", session=session)
+
+    assert mock_a2a_client.last_message is not None
+    assert mock_a2a_client.last_message.context_id == "svc-session-42"
+
+
+@mark.asyncio
+async def test_run_message_context_id_takes_precedence_over_session(mock_a2a_client: MockA2AClient) -> None:
+    """Test that an explicit context_id on the message wins over session.service_session_id."""
+    agent = A2AAgent(name="Test Agent", id="test-agent", client=mock_a2a_client, http_client=None)
+    mock_a2a_client.add_message_response("msg-ctx2", "reply")
+
+    session = AgentSession(service_session_id="svc-session-42")
+    message = Message(
+        role="user",
+        contents=[Content.from_text(text="Hello")],
+        additional_properties={"context_id": "explicit-ctx"},
+    )
+    await agent.run(messages=[message], session=session)
+
+    assert mock_a2a_client.last_message is not None
+    assert mock_a2a_client.last_message.context_id == "explicit-ctx"
+
+
+# endregion
+
+
 # region Context Provider Tests
 
 

python/packages/ag-ui/agent_framework_ag_ui/_agent_run.py

@@ -790,9 +790,9 @@ async def run_agent_stream(
     # Create session (with service session support)
     if config.use_service_session:
         supplied_thread_id = input_data.get("thread_id") or input_data.get("threadId")
-        session = AgentSession(service_session_id=supplied_thread_id)
+        session = AgentSession(session_id=thread_id, service_session_id=supplied_thread_id)
     else:
-        session = AgentSession()
+        session = AgentSession(session_id=thread_id)
 
     # Inject metadata for AG-UI orchestration (Feature #2: Azure-safe truncation)
     base_metadata: dict[str, Any] = {

python/packages/ag-ui/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agent-framework-ag-ui"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 description = "AG-UI protocol integration for Agent Framework"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "ag-ui-protocol==0.1.13",
     "fastapi>=0.115.0,<0.133.1",
     "uvicorn[standard]>=0.30.0,<0.42.0"

python/packages/ag-ui/tests/ag_ui/conftest.py

@@ -183,6 +183,7 @@ class StubAgent(SupportsAgentRun):
         self.client = client or SimpleNamespace(function_invocation_configuration=None)
         self.messages_received: list[Any] = []
         self.tools_received: list[Any] | None = None
+        self.last_session: AgentSession | None = None
 
     @overload
     def run(
@@ -216,6 +217,7 @@ class StubAgent(SupportsAgentRun):
 
             async def _stream() -> AsyncIterator[AgentResponseUpdate]:
                 self.messages_received = [] if messages is None else list(messages)  # type: ignore[arg-type]
+                self.last_session = session
                 self.tools_received = kwargs.get("tools")
                 for update in self.updates:
                     yield update

python/packages/ag-ui/tests/ag_ui/test_run.py

@@ -1640,3 +1640,115 @@ class TestReasoningInSnapshot:
         # close: MsgEnd(block2) + End(block2)
         assert isinstance(close[0], ReasoningMessageEndEvent)
         assert close[0].message_id == "block2"
+
+
+async def test_session_id_matches_thread_id():
+    """Session created by run_agent_stream uses the client thread_id as session_id."""
+    from conftest import StubAgent
+
+    from agent_framework_ag_ui import AgentFrameworkAgent
+
+    stub = StubAgent()
+    agent = AgentFrameworkAgent(agent=stub)
+
+    payload = {
+        "thread_id": "my-thread-123",
+        "run_id": "run-1",
+        "messages": [{"role": "user", "content": "Hello"}],
+    }
+
+    _ = [event async for event in agent.run(payload)]
+
+    assert stub.last_session is not None
+    assert stub.last_session.session_id == "my-thread-123"
+
+
+async def test_session_id_matches_camel_case_thread_id():
+    """Session uses threadId (camelCase) as session_id when snake_case is absent."""
+    from conftest import StubAgent
+
+    from agent_framework_ag_ui import AgentFrameworkAgent
+
+    stub = StubAgent()
+    agent = AgentFrameworkAgent(agent=stub)
+
+    payload = {
+        "threadId": "camel-thread-456",
+        "run_id": "run-2",
+        "messages": [{"role": "user", "content": "Hello"}],
+    }
+
+    _ = [event async for event in agent.run(payload)]
+
+    assert stub.last_session is not None
+    assert stub.last_session.session_id == "camel-thread-456"
+
+
+async def test_session_id_matches_thread_id_with_service_session():
+    """Session uses thread_id as session_id even when use_service_session is enabled."""
+    from conftest import StubAgent
+
+    from agent_framework_ag_ui import AgentFrameworkAgent
+
+    stub = StubAgent()
+    agent = AgentFrameworkAgent(agent=stub, use_service_session=True)
+
+    payload = {
+        "thread_id": "service-thread-789",
+        "run_id": "run-3",
+        "messages": [{"role": "user", "content": "Hello"}],
+    }
+
+    _ = [event async for event in agent.run(payload)]
+
+    assert stub.last_session is not None
+    assert stub.last_session.session_id == "service-thread-789"
+    assert stub.last_session.service_session_id == "service-thread-789"
+
+
+async def test_session_id_generated_when_no_thread_id():
+    """Session gets a generated UUID as session_id when no thread_id is provided."""
+    import uuid
+
+    from conftest import StubAgent
+
+    from agent_framework_ag_ui import AgentFrameworkAgent
+
+    stub = StubAgent()
+    agent = AgentFrameworkAgent(agent=stub)
+
+    payload = {
+        "run_id": "run-4",
+        "messages": [{"role": "user", "content": "Hello"}],
+    }
+
+    _ = [event async for event in agent.run(payload)]
+
+    assert stub.last_session is not None
+    # Should be a valid UUID (auto-generated)
+    uuid.UUID(stub.last_session.session_id)
+
+
+async def test_service_session_no_thread_id_generates_uuid():
+    """With use_service_session=True and no thread_id, session_id is a UUID and service_session_id is None."""
+    import uuid
+
+    from conftest import StubAgent
+
+    from agent_framework_ag_ui import AgentFrameworkAgent
+
+    stub = StubAgent()
+    agent = AgentFrameworkAgent(agent=stub, use_service_session=True)
+
+    payload = {
+        "run_id": "run-5",
+        "messages": [{"role": "user", "content": "Hello"}],
+    }
+
+    _ = [event async for event in agent.run(payload)]
+
+    assert stub.last_session is not None
+    # session_id should be a valid auto-generated UUID
+    uuid.UUID(stub.last_session.session_id)
+    # service_session_id should be None since no thread_id was supplied
+    assert stub.last_session.service_session_id is None

python/packages/anthropic/agent_framework_anthropic/_bedrock_client.py

@@ -6,13 +6,13 @@ from collections.abc import Sequence
 from typing import Any, ClassVar, Generic, TypedDict
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
     FunctionInvocationConfiguration,
     FunctionInvocationLayer,
 )
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 from anthropic import AsyncAnthropicBedrock
 
@@ -94,7 +94,7 @@ class RawAnthropicBedrockClient(RawAnthropicClient[AnthropicOptionsT], Generic[A
                 aws_profile=settings.get("aws_profile"),
                 aws_session_token=session_token_secret.get_secret_value() if session_token_secret is not None else None,
                 base_url=settings.get("anthropic_bedrock_base_url"),
-                default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+                default_headers={"User-Agent": get_user_agent()},
             )
 
         super().__init__(

python/packages/anthropic/agent_framework_anthropic/_chat_client.py

@@ -8,7 +8,6 @@ from collections.abc import AsyncIterable, Awaitable, Callable, Mapping, Sequenc
 from typing import Any, ClassVar, Final, Generic, Literal, TypedDict
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     Annotation,
     BaseChatClient,
     ChatAndFunctionMiddlewareTypes,
@@ -28,6 +27,7 @@ from agent_framework import (
     tool,
 )
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework._tools import SHELL_TOOL_KIND_VALUE
 from agent_framework._types import _get_data_bytes_as_str  # type: ignore
 from agent_framework.observability import ChatTelemetryLayer
@@ -332,7 +332,7 @@ class RawAnthropicClient(
 
             anthropic_client = AsyncAnthropic(
                 api_key=api_key_secret.get_secret_value(),
-                default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+                default_headers={"User-Agent": get_user_agent()},
             )
 
         # Initialize parent
@@ -604,7 +604,7 @@ class RawAnthropicClient(
         run_options["betas"] = self._prepare_betas(options)
 
         # extra headers
-        run_options["extra_headers"] = {"User-Agent": AGENT_FRAMEWORK_USER_AGENT}
+        run_options["extra_headers"] = {"User-Agent": get_user_agent()}
 
         # Handle user option -> metadata.user_id (Anthropic uses metadata.user_id instead of user)
         if user := run_options.pop("user", None):

python/packages/anthropic/agent_framework_anthropic/_foundry_client.py

@@ -6,13 +6,13 @@ from collections.abc import Awaitable, Callable, Sequence
 from typing import Any, ClassVar, Generic, TypedDict
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
     FunctionInvocationConfiguration,
     FunctionInvocationLayer,
 )
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 from anthropic import AsyncAnthropicFoundry
 
@@ -91,14 +91,14 @@ class RawAnthropicFoundryClient(RawAnthropicClient[AnthropicOptionsT], Generic[A
                     base_url=base_url_setting,
                     api_key=api_key_value,
                     azure_ad_token_provider=azure_ad_token_provider,
-                    default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+                    default_headers={"User-Agent": get_user_agent()},
                 )
             else:
                 anthropic_client = AsyncAnthropicFoundry(
                     resource=resource_setting,
                     api_key=api_key_value,
                     azure_ad_token_provider=azure_ad_token_provider,
-                    default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+                    default_headers={"User-Agent": get_user_agent()},
                 )
 
         super().__init__(

python/packages/anthropic/agent_framework_anthropic/_vertex_client.py

@@ -6,13 +6,13 @@ from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, ClassVar, Generic, TypedDict
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
     FunctionInvocationConfiguration,
     FunctionInvocationLayer,
 )
 from agent_framework._settings import load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 from anthropic import NOT_GIVEN, AsyncAnthropicVertex
 
@@ -89,7 +89,7 @@ class RawAnthropicVertexClient(RawAnthropicClient[AnthropicOptionsT], Generic[An
                 access_token=access_token,
                 credentials=credentials,
                 base_url=settings.get("anthropic_vertex_base_url"),
-                default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+                default_headers={"User-Agent": get_user_agent()},
             )
 
         super().__init__(

python/packages/anthropic/pyproject.toml

@@ -4,7 +4,7 @@ description = "Anthropic integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "anthropic>=0.80.0,<0.80.1",
 ]
 

python/packages/anthropic/tests/test_anthropic_provider_clients.py

@@ -3,7 +3,8 @@
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-from agent_framework import AGENT_FRAMEWORK_USER_AGENT, ChatMiddlewareLayer, FunctionInvocationLayer
+from agent_framework import ChatMiddlewareLayer, FunctionInvocationLayer
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 
 from agent_framework_anthropic import (
@@ -61,7 +62,7 @@ def test_raw_anthropic_foundry_client_creates_sdk_client_from_settings(tmp_path)
         resource="test-resource",
         api_key="test-key",
         azure_ad_token_provider=None,
-        default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+        default_headers={"User-Agent": get_user_agent()},
     )
 
 
@@ -85,7 +86,7 @@ def test_raw_anthropic_foundry_client_creates_sdk_client_from_base_url_settings(
         base_url="https://test-resource.services.ai.azure.com/anthropic/",
         api_key="test-key",
         azure_ad_token_provider=None,
-        default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+        default_headers={"User-Agent": get_user_agent()},
     )
 
 
@@ -130,7 +131,7 @@ def test_raw_anthropic_bedrock_client_creates_sdk_client_from_arguments() -> Non
         aws_profile=None,
         aws_session_token=None,
         base_url=None,
-        default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+        default_headers={"User-Agent": get_user_agent()},
     )
 
 
@@ -152,5 +153,5 @@ def test_raw_anthropic_vertex_client_creates_sdk_client_from_arguments() -> None
         access_token=None,
         credentials=None,
         base_url=None,
-        default_headers={"User-Agent": AGENT_FRAMEWORK_USER_AGENT},
+        default_headers={"User-Agent": get_user_agent()},
     )

python/packages/azure-ai-search/agent_framework_azure_ai_search/_context_provider.py

@@ -14,7 +14,6 @@ from collections.abc import Awaitable, Callable
 from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypedDict, overload
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     AgentSession,
     Annotation,
     Content,
@@ -25,6 +24,7 @@ from agent_framework import (
     SupportsGetEmbeddings,
     load_settings,
 )
+from agent_framework._telemetry import get_user_agent
 from agent_framework.exceptions import SettingNotFoundError
 from azure.core.credentials import AzureKeyCredential, TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
@@ -535,7 +535,7 @@ class AzureAISearchContextProvider(ContextProvider):
                 endpoint=self.endpoint,
                 index_name=self.index_name,
                 credential=self.credential,
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                user_agent=get_user_agent(),
             )
 
         self._index_client: SearchIndexClient | None = None
@@ -544,7 +544,7 @@ class AzureAISearchContextProvider(ContextProvider):
             self._index_client = SearchIndexClient(
                 endpoint=self.endpoint,
                 credential=self.credential,
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                user_agent=get_user_agent(),
             )
 
         self._knowledge_base_initialized = False
@@ -640,7 +640,7 @@ class AzureAISearchContextProvider(ContextProvider):
                 self._index_client = SearchIndexClient(
                     endpoint=self.endpoint,
                     credential=self.credential,
-                    user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                    user_agent=get_user_agent(),
                 )
             if not self.index_name:
                 logger.warning("Cannot auto-discover vector field: index_name is not set.")
@@ -740,7 +740,7 @@ class AzureAISearchContextProvider(ContextProvider):
                     endpoint=self.endpoint,
                     knowledge_base_name=knowledge_base_name,
                     credential=self.credential,
-                    user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                    user_agent=get_user_agent(),
                 )
             self._knowledge_base_initialized = True
             return
@@ -802,7 +802,7 @@ class AzureAISearchContextProvider(ContextProvider):
                 endpoint=self.endpoint,
                 knowledge_base_name=knowledge_base_name,
                 credential=self.credential,
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                user_agent=get_user_agent(),
             )
 
     async def _agentic_search(self, messages: list[Message]) -> list[Message]:

python/packages/azure-ai-search/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure AI Search integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "azure-search-documents>=11.7.0b2,<11.7.0b3",
 ]
 

python/packages/azure-cosmos/agent_framework_azure_cosmos/_checkpoint_storage.py

@@ -7,8 +7,8 @@ from __future__ import annotations
 import logging
 from typing import Any, TypedDict
 
-from agent_framework import AGENT_FRAMEWORK_USER_AGENT
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework._workflows._checkpoint import CheckpointID, WorkflowCheckpoint
 from agent_framework._workflows._checkpoint_encoding import decode_checkpoint_value, encode_checkpoint_value
 from agent_framework.exceptions import WorkflowCheckpointException
@@ -194,7 +194,7 @@ class CosmosCheckpointStorage:
             self._cosmos_client = CosmosClient(
                 url=settings["endpoint"],  # type: ignore[arg-type]
                 credential=credential or settings["key"].get_secret_value(),  # type: ignore[arg-type,union-attr]
-                user_agent_suffix=AGENT_FRAMEWORK_USER_AGENT,
+                user_agent_suffix=get_user_agent(),
             )
             self._owns_client = True
 

python/packages/azure-cosmos/agent_framework_azure_cosmos/_history_provider.py

@@ -10,9 +10,10 @@ import uuid
 from collections.abc import Sequence
 from typing import Any, ClassVar, TypedDict
 
-from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Message
+from agent_framework import Message
 from agent_framework._sessions import HistoryProvider
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
 from azure.cosmos import PartitionKey
@@ -121,7 +122,7 @@ class CosmosHistoryProvider(HistoryProvider):
             self._cosmos_client = CosmosClient(
                 url=settings["endpoint"],  # type: ignore[arg-type]
                 credential=credential or settings["key"].get_secret_value(),  # type: ignore[arg-type,union-attr]
-                user_agent_suffix=AGENT_FRAMEWORK_USER_AGENT,
+                user_agent_suffix=get_user_agent(),
             )
             self._owns_client = True
 

python/packages/azure-cosmos/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure Cosmos DB history provider integration for Microsoft Agent
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "azure-cosmos>=4.3.0,<5",
 ]
 

python/packages/azurefunctions/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure Functions integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "agent-framework-durabletask",
     "azure-functions>=1.24.0,<2",
     "azure-functions-durable>=1.3.1,<2",

python/packages/bedrock/agent_framework_bedrock/_chat_client.py

@@ -13,7 +13,6 @@ from typing import Any, ClassVar, Generic, Literal, TypedDict
 from uuid import uuid4
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     BaseChatClient,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
@@ -31,6 +30,7 @@ from agent_framework import (
     validate_tool_mode,
 )
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework.exceptions import ChatClientInvalidResponseException
 from agent_framework.observability import ChatTelemetryLayer
 from boto3.session import Session as Boto3Session
@@ -299,7 +299,7 @@ class BedrockChatClient(
             self._bedrock_client = session.client(
                 "bedrock-runtime",
                 region_name=region,
-                config=BotoConfig(user_agent_extra=AGENT_FRAMEWORK_USER_AGENT),
+                config=BotoConfig(user_agent_extra=get_user_agent()),
             )
 
         super().__init__(

python/packages/bedrock/agent_framework_bedrock/_embedding_client.py

@@ -11,7 +11,6 @@ from collections.abc import Sequence
 from typing import Any, ClassVar, Generic, TypedDict
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     BaseEmbeddingClient,
     Embedding,
     EmbeddingGenerationOptions,
@@ -20,6 +19,7 @@ from agent_framework import (
     UsageDetails,
     load_settings,
 )
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import EmbeddingTelemetryLayer
 from boto3.session import Session as Boto3Session
 from botocore.client import BaseClient
@@ -140,7 +140,7 @@ class RawBedrockEmbeddingClient(
             self._bedrock_client = boto3_session.client(
                 "bedrock-runtime",
                 region_name=region_name or resolved_region,
-                config=BotoConfig(user_agent_extra=AGENT_FRAMEWORK_USER_AGENT),
+                config=BotoConfig(user_agent_extra=get_user_agent()),
             )
 
         self.model: str = settings["embedding_model"]  # type: ignore[assignment]  # pyright: ignore[reportTypedDictNotRequiredAccess]

python/packages/bedrock/pyproject.toml

@@ -4,7 +4,7 @@ description = "Amazon Bedrock integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "boto3>=1.35.0,<2.0.0",
     "botocore>=1.35.0,<2.0.0",
 ]

python/packages/chatkit/pyproject.toml

@@ -4,7 +4,7 @@ description = "OpenAI ChatKit integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "openai-chatkit>=1.4.1,<2.0.0",
 ]
 

python/packages/claude/pyproject.toml

@@ -4,7 +4,7 @@ description = "Claude Agent SDK integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "claude-agent-sdk>=0.1.36,<0.1.49",
 ]
 

python/packages/copilotstudio/pyproject.toml

@@ -4,7 +4,7 @@ description = "Copilot Studio integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "microsoft-agents-copilotstudio-client>=0.3.1,<0.3.2",
 ]
 

python/packages/core/agent_framework/__init__.py

@@ -125,6 +125,7 @@ from ._telemetry import (
     prepend_agent_framework_to_user_agent,
 )
 from ._tools import (
+    SKIP_PARSING,
     FunctionInvocationConfiguration,
     FunctionInvocationLayer,
     FunctionTool,
@@ -258,6 +259,7 @@ __all__ = [
     "GROUP_INDEX_KEY",
     "GROUP_KIND_KEY",
     "GROUP_TOKEN_COUNT_KEY",
+    "SKIP_PARSING",
     "SUMMARIZED_BY_SUMMARY_ID_KEY",
     "SUMMARY_OF_GROUP_IDS_KEY",
     "SUMMARY_OF_MESSAGE_IDS_KEY",

python/packages/core/agent_framework/_telemetry.py

@@ -4,9 +4,6 @@ from __future__ import annotations
 
 import logging
 import os
-from collections.abc import Generator
-from contextlib import contextmanager
-from contextvars import ContextVar
 from typing import Any, Final
 
 from . import __version__ as version_info
@@ -29,34 +26,73 @@ USER_AGENT_KEY: Final[str] = "User-Agent"
 HTTP_USER_AGENT: Final[str] = "agent-framework-python"
 AGENT_FRAMEWORK_USER_AGENT = f"{HTTP_USER_AGENT}/{version_info}"  # type: ignore[has-type]
 
-_user_agent_prefixes: ContextVar[tuple[str, ...]] = ContextVar("_user_agent_prefixes", default=())
+# This environment variable is reserved by the Foundry hosting environment to
+# indicate that the agent is running in a hosted environment.
+_FOUNDRY_HOSTING_ENV_VAR = "FOUNDRY_HOSTING_ENVIRONMENT"
+# This prefix is added to the user agent string when the agent is running in a hosted environment.
+_HOSTED_USER_AGENT_PREFIX = "foundry-hosting"
+
+_user_agent_prefixes: set[str] = set()
+_hosted_env_detected: bool = False
 
 
-@contextmanager
-def user_agent_prefix(prefix: str) -> Generator[None]:
-    """Context manager that adds a prefix to the user agent string for the current scope.
+def _add_user_agent_prefix(prefix: str) -> None:
+    """Permanently add a prefix to the user agent string.
 
-    This is useful for upstream layers that want to identify themselves in telemetry
-    for the duration of a request without permanently mutating global state.
+    This is used by hosting layers to identify themselves in telemetry.
+    Once added, the prefix applies to all subsequent user agent strings.
 
     Args:
         prefix: The prefix to add (e.g. "foundry-hosting").
     """
-    current = _user_agent_prefixes.get()
-    token = _user_agent_prefixes.set((*current, prefix)) if prefix and prefix not in current else None
+    if prefix:
+        _user_agent_prefixes.add(prefix)
+
+
+def _detect_hosted_environment() -> None:
+    """Detect if running in a hosted environment and add the user agent prefix.
+
+    Checks the ``FOUNDRY_HOSTING_ENVIRONMENT`` env var first, then falls back
+    to checking whether the agent server SDK is installed (via
+    ``importlib.util.find_spec``) before importing it, to avoid unnecessary
+    import overhead for non-hosted scenarios.
+    """
+    global _hosted_env_detected
+    if _hosted_env_detected:
+        return
+    _hosted_env_detected = True
+
+    env_value = os.environ.get(_FOUNDRY_HOSTING_ENV_VAR)
+    if env_value is not None:
+        # Env var exists — trust its value and skip the fallback.
+        if env_value:
+            _add_user_agent_prefix(_HOSTED_USER_AGENT_PREFIX)
+        return
+
+    # Env var not set — fall back to AgentConfig as a second layer of defense.
+    # Use find_spec to avoid the cost of a full import when the SDK is not installed.
+    import importlib.util
+
     try:
-        yield
-    finally:
-        if token is not None:
-            _user_agent_prefixes.reset(token)
+        if importlib.util.find_spec("azure.ai.agentserver.core") is None:
+            return
+    except (ModuleNotFoundError, ValueError):
+        return
+    try:
+        from azure.ai.agentserver.core import AgentConfig  # pyright: ignore[reportMissingImports]
+
+        if AgentConfig.from_env().is_hosted:
+            _add_user_agent_prefix(_HOSTED_USER_AGENT_PREFIX)
+    except (ImportError, AttributeError):
+        pass
 
 
-def _get_user_agent() -> str:
-    """Return the full user agent string including any context-scoped prefixes."""
-    prefixes = _user_agent_prefixes.get()
-    if not prefixes:
+def get_user_agent() -> str:
+    """Return the full user agent string including any registered prefixes."""
+    _detect_hosted_environment()
+    if not _user_agent_prefixes:
         return AGENT_FRAMEWORK_USER_AGENT
-    return f"{'/'.join(prefixes)}/{AGENT_FRAMEWORK_USER_AGENT}"
+    return f"{'/'.join(sorted(_user_agent_prefixes))}/{AGENT_FRAMEWORK_USER_AGENT}"
 
 
 def prepend_agent_framework_to_user_agent(headers: dict[str, Any] | None = None) -> dict[str, Any]:
@@ -89,7 +125,7 @@ def prepend_agent_framework_to_user_agent(headers: dict[str, Any] | None = None)
     """
     if not IS_TELEMETRY_ENABLED:
         return headers or {}
-    user_agent = _get_user_agent()
+    user_agent = get_user_agent()
     if not headers:
         return {USER_AGENT_KEY: user_agent}
     headers[USER_AGENT_KEY] = f"{user_agent} {headers[USER_AGENT_KEY]}" if USER_AGENT_KEY in headers else user_agent

python/packages/core/agent_framework/_tools.py

@@ -94,6 +94,33 @@ ApprovalMode: TypeAlias = Literal["always_require", "never_require"]
 ChatClientT = TypeVar("ChatClientT", bound="SupportsChatGetResponse[Any]")
 ResponseModelBoundT = TypeVar("ResponseModelBoundT", bound=BaseModel)
 
+
+class _SkipParsingSentinel:
+    """Sentinel signaling that :meth:`FunctionTool.invoke` should return the raw value.
+
+    When passed as ``result_parser`` to :class:`FunctionTool` (or the ``@tool`` decorator),
+    the default :meth:`FunctionTool.parse_result` is bypassed and the wrapped function's
+    return value is returned unchanged from :meth:`FunctionTool.invoke`. Callers may also
+    request the raw value on a per-call basis by passing ``skip_parsing=True`` to
+    :meth:`FunctionTool.invoke`.
+
+    Use the module-level ``SKIP_PARSING`` singleton — do not instantiate this class.
+    """
+
+    _instance: ClassVar[_SkipParsingSentinel | None] = None
+
+    def __new__(cls) -> _SkipParsingSentinel:
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+        return cls._instance
+
+    def __repr__(self) -> str:
+        return "SKIP_PARSING"
+
+
+SKIP_PARSING: Final[_SkipParsingSentinel] = _SkipParsingSentinel()
+"""Sentinel for ``FunctionTool(result_parser=...)`` meaning "do not parse the result"."""
+
 # region Helpers
 
 
@@ -279,7 +306,7 @@ class FunctionTool(SerializationMixin):
         additional_properties: dict[str, Any] | None = None,
         func: Callable[..., Any] | None = None,
         input_model: type[BaseModel] | Mapping[str, Any] | None = None,
-        result_parser: Callable[[Any], str | list[Content]] | None = None,
+        result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
         **kwargs: Any,
     ) -> None:
         """Initialize the FunctionTool.
@@ -327,9 +354,11 @@ class FunctionTool(SerializationMixin):
             result_parser: An optional callable with signature ``Callable[[Any], str]`` that
                 overrides the default result parsing behavior. When provided, this callable
                 is used to convert the raw function return value to a string instead of the
-                built-in :meth:`parse_result` logic. Depending on your function, it may be
-                easiest to just do the serialization directly in the function body rather
-                than providing a custom ``result_parser``.
+                built-in :meth:`parse_result` logic. Pass the :data:`SKIP_PARSING` sentinel
+                instead of a callable to opt out of parsing entirely; in that case
+                :meth:`invoke` returns the wrapped function's raw return value. Depending
+                on your function, it may be easiest to just do the serialization directly
+                in the function body rather than providing a custom ``result_parser``.
             **kwargs: Additional keyword arguments.
         """
         # Core attributes (formerly from BaseTool)
@@ -508,31 +537,65 @@ class FunctionTool(SerializationMixin):
             self.invocation_exception_count += 1
             raise
 
+    @overload
     async def invoke(
         self,
         *,
         arguments: BaseModel | Mapping[str, Any] | None = None,
         context: FunctionInvocationContext | None = None,
         tool_call_id: str | None = None,
+        skip_parsing: Literal[True],
         **kwargs: Any,
-    ) -> list[Content]:
+    ) -> Any: ...
+
+    @overload
+    async def invoke(
+        self,
+        *,
+        arguments: BaseModel | Mapping[str, Any] | None = None,
+        context: FunctionInvocationContext | None = None,
+        tool_call_id: str | None = None,
+        skip_parsing: Literal[False] = False,
+        **kwargs: Any,
+    ) -> list[Content]: ...
+
+    async def invoke(
+        self,
+        *,
+        arguments: BaseModel | Mapping[str, Any] | None = None,
+        context: FunctionInvocationContext | None = None,
+        tool_call_id: str | None = None,
+        skip_parsing: bool = False,
+        **kwargs: Any,
+    ) -> list[Content] | Any:
         """Run the AI function with the provided arguments as a Pydantic model.
 
         The raw return value of the wrapped function is automatically parsed into a
         ``list[Content]`` using :meth:`parse_result` or the custom ``result_parser``
-        if one was provided.  Every result — text, rich media, or serialized objects —
-        is represented uniformly as Content items.
+        configured on the tool. Every result — text, rich media, or serialized
+        objects — is represented uniformly as Content items.
+
+        Parsing can be skipped in two ways: configure the tool with
+        ``result_parser=SKIP_PARSING`` to always skip parsing, or pass
+        ``skip_parsing=True`` per call. Either way the wrapped function's raw value
+        is returned. This is intended for callers (e.g. sandboxed runtimes) that
+        consume the value from Python directly and would otherwise undo the
+        ``Content`` wrapping.
 
         Keyword Args:
             arguments: A mapping or model instance containing the arguments for the function.
             context: Explicit function invocation context carrying runtime kwargs.
             tool_call_id: Optional tool call identifier used for telemetry and tracing.
+            skip_parsing: When ``True``, bypass parsing and return the wrapped function's
+                raw value instead of a ``list[Content]``. Defaults to ``False``.
             kwargs: Direct function argument values. When provided, every keyword
                 must match a declared tool parameter. Runtime data must be passed
                 via ``context``.
 
         Returns:
-            A list of Content items representing the tool output.
+            ``list[Content]`` by default. The raw function return value (``Any``) when
+            ``skip_parsing=True`` (or the tool was constructed with
+            ``result_parser=SKIP_PARSING``).
 
         Raises:
             TypeError: If arguments is not mapping-like or fails schema checks.
@@ -544,7 +607,9 @@ class FunctionTool(SerializationMixin):
         from ._types import Content
         from .observability import OBSERVABILITY_SETTINGS
 
-        parser = self.result_parser or FunctionTool.parse_result
+        configured_parser = self.result_parser
+        skip_parsing = skip_parsing or configured_parser is SKIP_PARSING
+        parser = configured_parser if callable(configured_parser) else FunctionTool.parse_result
 
         parameter_names = set(self.parameters().get("properties", {}).keys())
         direct_argument_kwargs = (
@@ -616,6 +681,10 @@ class FunctionTool(SerializationMixin):
             logger.debug(f"Function arguments: {observable_kwargs}")
             res = self.__call__(**call_kwargs)
             result = await res if inspect.isawaitable(res) else res
+            if skip_parsing:
+                logger.info(f"Function {self.name} succeeded.")
+                logger.debug(f"Function result: {type(result).__name__}")
+                return result
             try:
                 parsed = parser(result)
             except Exception:
@@ -671,6 +740,13 @@ class FunctionTool(SerializationMixin):
                 logger.error(f"Function failed. Error: {exception}")
                 raise
             else:
+                if skip_parsing:
+                    logger.info(f"Function {self.name} succeeded.")
+                    if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED:  # type: ignore[name-defined]
+                        result_str = str(result)
+                        span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
+                        logger.debug(f"Function result: {result_str}")
+                    return result
                 try:
                     parsed = parser(result)
                 except Exception:
@@ -1067,7 +1143,7 @@ def tool(
     max_invocations: int | None = None,
     max_invocation_exceptions: int | None = None,
     additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
 ) -> FunctionTool: ...
 
 
@@ -1083,7 +1159,7 @@ def tool(
     max_invocations: int | None = None,
     max_invocation_exceptions: int | None = None,
     additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
 ) -> Callable[[Callable[..., Any]], FunctionTool]: ...
 
 
@@ -1098,7 +1174,7 @@ def tool(
     max_invocations: int | None = None,
     max_invocation_exceptions: int | None = None,
     additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
 ) -> FunctionTool | Callable[[Callable[..., Any]], FunctionTool]:
     """Decorate a function to turn it into a FunctionTool that can be passed to models and executed automatically.
 

python/packages/core/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.0"
+version = "1.1.1"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"

python/packages/core/tests/core/test_telemetry.py

@@ -1,14 +1,21 @@
 # Copyright (c) Microsoft. All rights reserved.
 
-from unittest.mock import patch
+import os
+from unittest.mock import MagicMock, patch
 
+import agent_framework._telemetry as _telemetry_mod
 from agent_framework import (
     AGENT_FRAMEWORK_USER_AGENT,
     USER_AGENT_KEY,
     USER_AGENT_TELEMETRY_DISABLED_ENV_VAR,
     prepend_agent_framework_to_user_agent,
 )
-from agent_framework._telemetry import user_agent_prefix
+from agent_framework._telemetry import (
+    _FOUNDRY_HOSTING_ENV_VAR,
+    _HOSTED_USER_AGENT_PREFIX,
+    _add_user_agent_prefix,
+    _detect_hosted_environment,
+)
 
 # region Test constants
 
@@ -83,7 +90,7 @@ def test_prepend_to_empty_headers():
 
 def test_prepend_to_empty_dict():
     """Test prepending to empty headers dict."""
-    headers = {}
+    headers: dict[str, str] = {}
     result = prepend_agent_framework_to_user_agent(headers)
 
     assert "User-Agent" in result
@@ -99,54 +106,184 @@ def test_modifies_original_dict():
     assert "User-Agent" in headers
 
 
-# region Test user_agent_prefix context manager
+# region Test _add_user_agent_prefix
 
 
-def test_user_agent_prefix_adds_prefix():
-    """Test that the context manager adds a prefix within its scope."""
-    with user_agent_prefix("test-host"):
-        result = prepend_agent_framework_to_user_agent()
-        assert result["User-Agent"].startswith("test-host/")
-        assert AGENT_FRAMEWORK_USER_AGENT in result["User-Agent"]
-
-    # Prefix is removed after exiting the context
+def test_add_user_agent_prefix_adds_prefix():
+    """Test that _add_user_agent_prefix permanently adds a prefix."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _add_user_agent_prefix("test-host")
     result = prepend_agent_framework_to_user_agent()
-    assert result["User-Agent"] == AGENT_FRAMEWORK_USER_AGENT
+    assert result["User-Agent"].startswith("test-host/")
+    assert AGENT_FRAMEWORK_USER_AGENT in result["User-Agent"]
+    _telemetry_mod._user_agent_prefixes.clear()
 
 
-def test_user_agent_prefix_ignores_duplicates():
-    """Test that duplicate prefixes are not added within nested scopes."""
-    with user_agent_prefix("test-host"), user_agent_prefix("test-host"):
-        result = prepend_agent_framework_to_user_agent()
-        assert result["User-Agent"].count("test-host") == 1
+def test_add_user_agent_prefix_ignores_duplicates():
+    """Test that duplicate prefixes are not added."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _add_user_agent_prefix("test-host")
+    _add_user_agent_prefix("test-host")
+    result = prepend_agent_framework_to_user_agent()
+    assert result["User-Agent"].count("test-host") == 1
+    _telemetry_mod._user_agent_prefixes.clear()
 
 
-def test_user_agent_prefix_ignores_empty():
+def test_add_user_agent_prefix_ignores_empty():
     """Test that empty strings are not added as prefixes."""
-    with user_agent_prefix(""):
-        result = prepend_agent_framework_to_user_agent()
-        assert result["User-Agent"] == AGENT_FRAMEWORK_USER_AGENT
-
-
-def test_user_agent_prefix_restores_on_exit():
-    """Test that prefixes are fully restored after the context manager exits."""
-    with user_agent_prefix("test-host"):
-        pass
+    _telemetry_mod._user_agent_prefixes.clear()
+    _add_user_agent_prefix("")
     result = prepend_agent_framework_to_user_agent()
     assert result["User-Agent"] == AGENT_FRAMEWORK_USER_AGENT
+    _telemetry_mod._user_agent_prefixes.clear()
 
 
-def test_user_agent_prefix_nesting():
-    """Test that nested context managers compose prefixes correctly."""
-    with user_agent_prefix("outer"):
-        with user_agent_prefix("inner"):
-            result = prepend_agent_framework_to_user_agent()
-            assert "outer" in result["User-Agent"]
-            assert "inner" in result["User-Agent"]
-        # Inner prefix removed
-        result = prepend_agent_framework_to_user_agent()
-        assert "outer" in result["User-Agent"]
-        assert "inner" not in result["User-Agent"]
-    # Both removed
+def test_add_user_agent_prefix_multiple():
+    """Test that multiple prefixes compose correctly."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _add_user_agent_prefix("outer")
+    _add_user_agent_prefix("inner")
     result = prepend_agent_framework_to_user_agent()
-    assert result["User-Agent"] == AGENT_FRAMEWORK_USER_AGENT
+    assert "outer" in result["User-Agent"]
+    assert "inner" in result["User-Agent"]
+    _telemetry_mod._user_agent_prefixes.clear()
+
+
+# region Test _detect_hosted_environment
+
+
+def test_detect_hosted_env_var_truthy_adds_prefix():
+    """Test that a truthy FOUNDRY_HOSTING_ENVIRONMENT env var adds the prefix."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    with patch.dict("os.environ", {_FOUNDRY_HOSTING_ENV_VAR: "production"}):
+        _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+def test_detect_hosted_env_var_empty_skips_prefix():
+    """Test that an empty FOUNDRY_HOSTING_ENVIRONMENT env var does NOT add the prefix."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    with patch.dict("os.environ", {_FOUNDRY_HOSTING_ENV_VAR: ""}):
+        _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX not in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+def test_detect_hosted_env_var_set_skips_agent_config_fallback():
+    """Test that when the env var is set, AgentConfig is never consulted even if import would fail."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    import builtins
+
+    real_import = builtins.__import__
+
+    def _block_agentconfig(name: str, *args, **kwargs):  # type: ignore[no-untyped-def]
+        if "agentserver" in name:
+            raise AssertionError("AgentConfig should not be imported when env var is set")
+        return real_import(name, *args, **kwargs)
+
+    with (
+        patch.dict("os.environ", {_FOUNDRY_HOSTING_ENV_VAR: "prod"}),
+        patch("builtins.__import__", side_effect=_block_agentconfig),
+    ):
+        _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+def _mock_agent_config(*, is_hosted: bool) -> MagicMock:
+    """Create a mock azure.ai.agentserver.core module with AgentConfig."""
+    mock_config = MagicMock()
+    mock_config.is_hosted = is_hosted
+    mock_module = MagicMock()
+    mock_module.AgentConfig.from_env.return_value = mock_config
+    return mock_module
+
+
+def test_detect_hosted_fallback_agent_config_is_hosted():
+    """Test that AgentConfig fallback adds the prefix when is_hosted is True."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    env = {k: v for k, v in os.environ.items() if k != _FOUNDRY_HOSTING_ENV_VAR}
+    mock_module = _mock_agent_config(is_hosted=True)
+    mock_spec = MagicMock()
+    with (
+        patch.dict("os.environ", env, clear=True),
+        patch.dict("sys.modules", {"azure.ai.agentserver.core": mock_module}),
+        patch("importlib.util.find_spec", return_value=mock_spec),
+    ):
+        _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+def test_detect_hosted_fallback_agent_config_not_hosted():
+    """Test that AgentConfig fallback does NOT add the prefix when is_hosted is False."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    mock_module = _mock_agent_config(is_hosted=False)
+    mock_spec = MagicMock()
+    env = {k: v for k, v in os.environ.items() if k != _FOUNDRY_HOSTING_ENV_VAR}
+    with (
+        patch.dict("os.environ", env, clear=True),
+        patch.dict("sys.modules", {"azure.ai.agentserver.core": mock_module}),
+        patch("importlib.util.find_spec", return_value=mock_spec),
+    ):
+        _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX not in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+def test_detect_hosted_fallback_import_error():
+    """Test that ImportError from AgentConfig is silently handled."""
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    env = {k: v for k, v in os.environ.items() if k != _FOUNDRY_HOSTING_ENV_VAR}
+    with patch.dict("os.environ", env, clear=True):
+        # The real import may succeed or fail depending on the environment;
+        # force the ImportError path by making the import raise.
+        import builtins
+
+        real_import = builtins.__import__
+
+        def _block_agentconfig(name: str, *args, **kwargs):  # type: ignore[no-untyped-def]
+            if "agentserver" in name:
+                raise ImportError("mocked")
+            return real_import(name, *args, **kwargs)
+
+        with patch("builtins.__import__", side_effect=_block_agentconfig):
+            _detect_hosted_environment()
+    assert _HOSTED_USER_AGENT_PREFIX not in _telemetry_mod._user_agent_prefixes
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+
+
+# region Test module-level auto-detection
+
+
+def test_lazy_detection_on_get_user_agent():
+    """Test that get_user_agent() lazily detects the hosted environment.
+
+    Since detection is deferred to the first ``get_user_agent()`` call,
+    this verifies the prefix is included without any explicit call to
+    ``_detect_hosted_environment()`` by consumer code.
+    """
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False
+    with patch.dict("os.environ", {_FOUNDRY_HOSTING_ENV_VAR: "production"}):
+        user_agent = _telemetry_mod.get_user_agent()
+
+    assert _HOSTED_USER_AGENT_PREFIX in _telemetry_mod._user_agent_prefixes
+    assert user_agent.startswith(f"{_HOSTED_USER_AGENT_PREFIX}/")
+
+    # Clean up
+    _telemetry_mod._user_agent_prefixes.clear()
+    _telemetry_mod._hosted_env_detected = False

python/packages/core/tests/core/test_tools.py

@@ -8,6 +8,7 @@ from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanE
 from pydantic import BaseModel
 
 from agent_framework import (
+    SKIP_PARSING,
     Content,
     FunctionTool,
     tool,
@@ -1300,4 +1301,165 @@ def test_normalize_tools_flattens_mapping_like_toolbox_with_tools_attr() -> None
     assert normalized[1] is standalone
 
 
+# region SKIP_PARSING sentinel & skip_parsing
+
+
+async def test_invoke_skip_parsing_returns_native_value() -> None:
+    """invoke(skip_parsing=True) returns the wrapped function's raw value."""
+
+    @tool
+    def get_weather(city: str) -> dict[str, Any]:
+        """Get the weather."""
+        return {"city": city, "temperature_c": 21.5, "conditions": "partly cloudy"}
+
+    raw = await get_weather.invoke(arguments={"city": "Seattle"}, skip_parsing=True)
+
+    assert isinstance(raw, dict)
+    assert raw == {"city": "Seattle", "temperature_c": 21.5, "conditions": "partly cloudy"}
+
+
+async def test_invoke_skip_parsing_passes_through_custom_objects() -> None:
+    """skip_parsing must not call str()/repr() on the result."""
+
+    class Custom:  # noqa: B903
+        def __init__(self, value: int) -> None:
+            self.value = value
+
+    @tool
+    def make() -> Custom:
+        """Make a custom object."""
+        return Custom(42)
+
+    raw = await make.invoke(skip_parsing=True)
+
+    assert isinstance(raw, Custom)
+    assert raw.value == 42
+
+
+async def test_invoke_skip_parsing_awaits_async_functions() -> None:
+    @tool
+    async def slow(x: int) -> int:
+        """Async tool."""
+        return x * 2
+
+    raw = await slow.invoke(arguments={"x": 21}, skip_parsing=True)
+    assert raw == 42
+
+
+async def test_invoke_skip_parsing_bypasses_configured_result_parser() -> None:
+    """The tool's own result_parser is bypassed when skip_parsing=True is requested."""
+    parser_calls: list[Any] = []
+
+    def parser(value: Any) -> str:
+        parser_calls.append(value)
+        return "PARSED"
+
+    @tool(result_parser=parser)
+    def make_dict() -> dict[str, int]:
+        """Returns a dict."""
+        return {"a": 1}
+
+    raw = await make_dict.invoke(skip_parsing=True)
+    assert raw == {"a": 1}
+    assert parser_calls == []
+
+    # Sanity: omitting skip_parsing still applies the configured parser.
+    parsed = await make_dict.invoke()
+    assert parsed[0].type == "text"
+    assert parsed[0].text == "PARSED"
+
+
+async def test_constructor_skip_parsing_sentinel_returns_raw_by_default() -> None:
+    """Constructing a tool with result_parser=SKIP_PARSING makes invoke return the raw value."""
+
+    @tool(result_parser=SKIP_PARSING)
+    def make_dict() -> dict[str, int]:
+        """Returns a dict."""
+        return {"a": 1}
+
+    raw = await make_dict.invoke()
+    assert raw == {"a": 1}
+
+
+async def test_invoke_skip_parsing_validates_arguments() -> None:
+    """Argument validation is shared with the default path."""
+
+    @tool
+    def adder(x: int, y: int) -> int:
+        """Add."""
+        return x + y
+
+    with pytest.raises(TypeError):
+        await adder.invoke(arguments={"x": "not-an-int", "y": 1}, skip_parsing=True)
+
+
+async def test_invoke_skip_parsing_rejects_unexpected_runtime_kwargs() -> None:
+    @tool
+    async def echo(message: str) -> str:
+        """Echo."""
+        return message
+
+    with pytest.raises(TypeError, match="Unexpected keyword argument"):
+        await echo.invoke(arguments={"message": "hi"}, skip_parsing=True, api_token="secret")
+
+
+async def test_invoke_skip_parsing_raises_for_declaration_only_tool() -> None:
+    declared = FunctionTool(name="dummy", description="declaration only")
+
+    from agent_framework.exceptions import ToolException
+
+    with pytest.raises(ToolException):
+        await declared.invoke(arguments={}, skip_parsing=True)
+
+
+async def test_invoke_skip_parsing_records_telemetry(span_exporter: InMemorySpanExporter) -> None:
+    """skip_parsing participates in OTEL spans and records str(raw) as TOOL_RESULT."""
+
+    @tool(name="raw_tool", description="raw tool")
+    def returns_dict(x: int) -> dict[str, int]:
+        """Returns a dict."""
+        return {"value": x}
+
+    span_exporter.clear()
+    raw = await returns_dict.invoke(arguments={"x": 5}, tool_call_id="raw_call", skip_parsing=True)
+
+    assert raw == {"value": 5}
+    spans = span_exporter.get_finished_spans()
+    assert len(spans) == 1
+    span = spans[0]
+    assert span.attributes[OtelAttr.TOOL_NAME] == "raw_tool"
+    assert span.attributes[OtelAttr.TOOL_CALL_ID] == "raw_call"
+    assert span.attributes[OtelAttr.TOOL_RESULT] == "{'value': 5}"
+
+
+async def test_invoke_default_path_records_parsed_telemetry(
+    span_exporter: InMemorySpanExporter,
+) -> None:
+    """Regression: omitting skip_parsing still records the parsed result in telemetry."""
+
+    def parser(value: Any) -> str:
+        return f"parsed:{value}"
+
+    @tool(name="parsed_tool", description="parsed", result_parser=parser)
+    def returns_int() -> int:
+        """Returns an int."""
+        return 7
+
+    span_exporter.clear()
+    parsed = await returns_int.invoke(tool_call_id="parsed_call")
+
+    assert parsed[0].text == "parsed:7"
+    spans = span_exporter.get_finished_spans()
+    assert len(spans) == 1
+    assert spans[0].attributes[OtelAttr.TOOL_RESULT] == "parsed:7"
+
+
+def test_skip_parsing_is_singleton() -> None:
+    """SKIP_PARSING is a singleton; instantiation returns the same object."""
+    from agent_framework._tools import _SkipParsingSentinel
+
+    assert _SkipParsingSentinel() is SKIP_PARSING
+    assert repr(SKIP_PARSING) == "SKIP_PARSING"
+
+
 # endregion

python/packages/declarative/pyproject.toml

@@ -4,7 +4,7 @@ description = "Declarative specification support for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "powerfx>=0.0.32,<0.0.35; python_version < '3.14'",
     "pyyaml>=6.0,<7.0",
 ]

python/packages/devui/pyproject.toml

@@ -4,7 +4,7 @@ description = "Debug UI for Microsoft Agent Framework with OpenAI-compatible API
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
  dependencies = [
-     "agent-framework-core>=1.1.0,<2",
+     "agent-framework-core>=1.1.1,<2",
      "openai>=1.99.0,<3",
      "opentelemetry-sdk>=1.39.0,<2",
      "fastapi>=0.115.0,<0.133.1",

python/packages/durabletask/pyproject.toml

@@ -4,7 +4,7 @@ description = "Durable Task integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "durabletask>=1.3.0,<2",
     "durabletask-azuremanaged>=1.3.0,<2",
     "python-dateutil>=2.8.0,<3",

python/packages/foundry/agent_framework_foundry/_agent.py

@@ -15,7 +15,6 @@ from collections.abc import Awaitable, Callable, Mapping, MutableMapping, Sequen
 from typing import TYPE_CHECKING, Any, ClassVar, Generic, cast
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     AgentMiddlewareLayer,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
@@ -28,6 +27,7 @@ from agent_framework import (
     load_settings,
 )
 from agent_framework._compaction import CompactionStrategy, TokenizerProtocol
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import AgentTelemetryLayer, ChatTelemetryLayer
 from agent_framework_openai._chat_client import OpenAIChatOptions, RawOpenAIChatClient
 from azure.ai.projects.aio import AIProjectClient
@@ -190,7 +190,7 @@ class RawFoundryAgentChatClient(  # type: ignore[misc]
             project_client_kwargs: dict[str, Any] = {
                 "endpoint": resolved_endpoint,
                 "credential": credential,
-                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": get_user_agent(),
             }
             if allow_preview is not None:
                 project_client_kwargs["allow_preview"] = allow_preview

python/packages/foundry/agent_framework_foundry/_chat_client.py

@@ -8,7 +8,6 @@ from collections.abc import Awaitable, Callable, Mapping, Sequence
 from typing import TYPE_CHECKING, Any, ClassVar, Generic, Literal
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     ChatMiddlewareLayer,
     Content,
     FunctionInvocationConfiguration,
@@ -17,6 +16,7 @@ from agent_framework import (
 )
 from agent_framework._compaction import CompactionStrategy, TokenizerProtocol
 from agent_framework._feature_stage import ExperimentalFeature, experimental
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 from agent_framework_openai._chat_client import OpenAIChatOptions, RawOpenAIChatClient
 from azure.ai.projects.aio import AIProjectClient
@@ -198,7 +198,7 @@ class RawFoundryChatClient(  # type: ignore[misc]
             project_client_kwargs: dict[str, Any] = {
                 "endpoint": project_endpoint,
                 "credential": credential,  # type: ignore[arg-type]
-                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": get_user_agent(),
             }
             if allow_preview is not None:
                 project_client_kwargs["allow_preview"] = allow_preview
@@ -455,8 +455,18 @@ class RawFoundryChatClient(  # type: ignore[misc]
 
         Returns:
             An MCPTool configuration ready to pass to an Agent.
+
+        Raises:
+            ValueError: If neither ``url`` nor ``project_connection_id`` is supplied
+                — one is required by the Foundry Responses API.
         """
-        mcp = FoundryMCPTool(server_label=name.replace(" ", "_"), server_url=url or "", **kwargs)
+        if not url and not project_connection_id:
+            raise ValueError("MCP tool requires either 'url' or 'project_connection_id' to be specified.")
+
+        mcp_kwargs: dict[str, Any] = {"server_label": name.replace(" ", "_"), **kwargs}
+        if url:
+            mcp_kwargs["server_url"] = url
+        mcp = FoundryMCPTool(**mcp_kwargs)
 
         if description:
             mcp["server_description"] = description

python/packages/foundry/agent_framework_foundry/_memory_provider.py

@@ -14,13 +14,13 @@ from contextlib import AbstractAsyncContextManager
 from typing import TYPE_CHECKING, Any, ClassVar
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     AgentSession,
     ContextProvider,
     Message,
     SessionContext,
     load_settings,
 )
+from agent_framework._telemetry import get_user_agent
 from azure.ai.projects.aio import AIProjectClient
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
@@ -119,7 +119,7 @@ class FoundryMemoryProvider(ContextProvider):
             project_client_kwargs: dict[str, Any] = {
                 "endpoint": resolved_endpoint,
                 "credential": credential,  # type: ignore[arg-type]
-                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": get_user_agent(),
             }
             if allow_preview is not None:
                 project_client_kwargs["allow_preview"] = allow_preview

python/packages/foundry/agent_framework_foundry/_tools.py

@@ -133,26 +133,55 @@ def select_toolbox_tools(
     return selected
 
 
+def _validate_hosted_tool_payload(sanitized: Mapping[str, Any]) -> None:
+    """Fail fast on hosted tool payloads that would always be rejected by the Responses API.
+
+    These mismatches are not injectable defaults — the caller must supply the
+    missing information — so surfacing a clear error here points at the toolbox
+    definition instead of letting the API return a generic 400.
+    """
+    tool_type = sanitized.get("type")
+    if tool_type == "file_search" and not sanitized.get("vector_store_ids"):
+        raise ValueError(
+            "'file_search' tool is missing required 'vector_store_ids'. "
+            "If this came from a Foundry toolbox, update the toolbox definition "
+            "to include at least one vector store ID."
+        )
+    if tool_type == "mcp" and not sanitized.get("server_url") and not sanitized.get("project_connection_id"):
+        raise ValueError(
+            "'mcp' tool is missing both 'server_url' and 'project_connection_id'. "
+            "If this came from a Foundry toolbox, update the toolbox definition "
+            "to include one of these."
+        )
+
+
 @experimental(feature_id=ExperimentalFeature.TOOLBOXES)
 def sanitize_foundry_response_tool(tool_item: Any) -> Any:
     """Return a Responses-API-safe tool payload for Foundry hosted tools.
 
-    Azure AI Projects toolbox reads can currently return hosted tool objects with
-    extra read-model decoration fields such as top-level ``name`` and
-    ``description``. Azure AI Foundry rejects at least ``name`` on Responses API
-    requests with:
+    Reconciles known mismatches between toolbox reads and the Responses API:
 
-    ``Unknown parameter: 'tools[0].name'``.
+    1. Toolbox reads can return hosted tool objects decorated with read-model
+       fields such as top-level ``name`` and ``description``. The Responses API
+       rejects at least ``name`` with ``Unknown parameter: 'tools[0].name'``.
+       These fields are stripped from non-function hosted tool payloads.
+    2. ``code_interpreter`` tools stored in a toolbox without a ``container``
+       field (the Azure SDK treats it as optional) are rejected by the Responses
+       API with ``Missing required parameter: 'tools[N].container'``. A default
+       ``{"type": "auto"}`` container is injected when absent.
+    3. Hosted tools that are structurally incomplete in ways that cannot be
+       defaulted (``file_search`` without ``vector_store_ids``, ``mcp`` without
+       either ``server_url`` or ``project_connection_id``) raise ``ValueError``
+       with a message that points at the toolbox definition.
 
-    We defensively strip these decoration fields for non-function hosted tools so
-    the round-trip
-    ``toolbox.tools -> Agent(..., tools=...) -> run()`` works, while the Azure
-    SDK/service behavior is corrected upstream.
+    These are workarounds until the toolbox/Responses proxy normalizes payloads
+    server-side.
     """
     if isinstance(tool_item, FoundryMCPTool):
         sanitized: dict[str, Any] = dict(cast("Mapping[str, Any]", tool_item))
         sanitized.pop("name", None)
         sanitized.pop("description", None)
+        _validate_hosted_tool_payload(sanitized)
         return sanitized
 
     if isinstance(tool_item, Mapping):
@@ -161,6 +190,9 @@ def sanitize_foundry_response_tool(tool_item: Any) -> Any:
             sanitized = dict(mapping)
             sanitized.pop("name", None)
             sanitized.pop("description", None)
+            if sanitized.get("type") == "code_interpreter" and "container" not in sanitized:
+                sanitized["container"] = {"type": "auto"}
+            _validate_hosted_tool_payload(sanitized)
             return sanitized
 
     return cast(Any, tool_item)

python/packages/foundry/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Foundry integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.0"
+version = "1.1.1"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "agent-framework-openai>=1.1.0,<2",
     "azure-ai-inference>=1.0.0b9,<1.0.0b10",
     "azure-ai-projects>=2.1.0,<3.0",

python/packages/foundry/tests/foundry/test_foundry_chat_client.py

@@ -12,7 +12,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 from agent_framework import ChatResponse, Content, Message, SupportsChatGetResponse, tool
-from agent_framework._telemetry import AGENT_FRAMEWORK_USER_AGENT
+from agent_framework._telemetry import get_user_agent
 from agent_framework.exceptions import ChatClientException, ChatClientInvalidRequestException
 from agent_framework_openai import OpenAIContentFilterException
 from azure.ai.projects.models import MCPTool as FoundryMCPTool
@@ -199,7 +199,7 @@ def test_init_with_project_endpoint_creates_project_client() -> None:
     assert factory.call_args.kwargs["endpoint"] == _TEST_FOUNDRY_PROJECT_ENDPOINT
     assert factory.call_args.kwargs["credential"] is credential
     assert factory.call_args.kwargs["allow_preview"] is True
-    assert factory.call_args.kwargs["user_agent"] == AGENT_FRAMEWORK_USER_AGENT
+    assert factory.call_args.kwargs["user_agent"] == get_user_agent()
 
 
 def test_init_with_empty_model_raises(monkeypatch: pytest.MonkeyPatch) -> None:
@@ -607,6 +607,14 @@ def test_get_mcp_tool_with_project_connection_id() -> None:
     assert tool_config["project_connection_id"] == "conn-123"
     assert tool_config["allowed_tools"] == ["search_docs"]
     assert tool_config["server_label"] == "Docs_MCP"
+    # ``server_url`` should not be fabricated when only a project connection is supplied.
+    assert "server_url" not in tool_config
+
+
+def test_get_mcp_tool_requires_url_or_project_connection_id() -> None:
+    """Missing both ``url`` and ``project_connection_id`` is always invalid."""
+    with pytest.raises(ValueError, match="url.*project_connection_id"):
+        FoundryChatClient.get_mcp_tool(name="x")
 
 
 def test_prepare_tools_for_openai_strips_extraneous_name_from_foundry_mcp_tool() -> None:
@@ -655,6 +663,103 @@ def test_prepare_tools_for_openai_strips_read_model_fields_from_toolbox_code_int
     assert "description" not in prepared
 
 
+def test_prepare_tools_for_openai_injects_default_container_for_code_interpreter_dict() -> None:
+    """Toolbox-returned code_interpreter without a container must get a default injected.
+
+    The Azure SDK treats ``container`` as optional, but the Responses API rejects
+    ``code_interpreter`` entries without one. The sanitizer backfills ``{"type": "auto"}``.
+    """
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    tool = {
+        "type": "code_interpreter",
+        "name": "code_interpreter_t6bbtm",
+    }
+
+    response_tools = client._prepare_tools_for_openai([tool])
+
+    assert len(response_tools) == 1
+    prepared = response_tools[0]
+    assert prepared["type"] == "code_interpreter"
+    assert prepared["container"] == {"type": "auto"}
+    assert "name" not in prepared
+
+
+def test_prepare_tools_for_openai_injects_default_container_for_code_interpreter_sdk_instance() -> None:
+    """SDK ``CodeInterpreterTool`` instances without a container must also be backfilled.
+
+    Reproduces the toolbox creation path that calls
+    ``CodeInterpreterTool(name="code_interpreter")`` without a container.
+    """
+    from azure.ai.projects.models import CodeInterpreterTool
+
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    response_tools = client._prepare_tools_for_openai([CodeInterpreterTool(name="code_interpreter")])
+
+    assert len(response_tools) == 1
+    prepared = response_tools[0]
+    assert prepared["type"] == "code_interpreter"
+    assert prepared["container"] == {"type": "auto"}
+    assert "name" not in prepared
+
+
+def test_prepare_tools_for_openai_preserves_existing_code_interpreter_container() -> None:
+    """An already-populated container must not be overwritten by the sanitizer."""
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    explicit_container = {"file_ids": ["file_123"], "type": "auto"}
+    tool = {"type": "code_interpreter", "container": explicit_container}
+
+    response_tools = client._prepare_tools_for_openai([tool])
+
+    assert response_tools[0]["container"] == explicit_container
+
+
+def test_prepare_tools_for_openai_rejects_file_search_without_vector_store_ids() -> None:
+    """``file_search`` without ``vector_store_ids`` is always invalid — surface a clear error."""
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    with pytest.raises(ValueError, match="vector_store_ids"):
+        client._prepare_tools_for_openai([{"type": "file_search", "name": "fs"}])
+
+
+def test_prepare_tools_for_openai_rejects_mcp_without_server_destination() -> None:
+    """``mcp`` with neither ``server_url`` nor ``project_connection_id`` is always invalid."""
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    tool = FoundryMCPTool(server_label="orphan")
+
+    with pytest.raises(ValueError, match="server_url.*project_connection_id"):
+        client._prepare_tools_for_openai([tool])
+
+
+def test_prepare_tools_for_openai_accepts_mcp_with_only_project_connection_id() -> None:
+    """MCP tools backed by a Foundry connection (no ``server_url``) must still pass validation."""
+    project_client = MagicMock()
+    project_client.get_openai_client.return_value = _make_mock_openai_client()
+    client = FoundryChatClient(project_client=project_client, model="test-model")
+
+    tool = FoundryMCPTool(server_label="githubmcp")
+    tool["project_connection_id"] = "githubmcp"
+
+    response_tools = client._prepare_tools_for_openai([tool])
+
+    assert len(response_tools) == 1
+    assert response_tools[0]["project_connection_id"] == "githubmcp"
+    assert "server_url" not in response_tools[0]
+
+
 def test_prepare_tools_for_openai_strips_name_from_non_function_hosted_tool_dicts() -> None:
     """All non-function hosted tool payloads should drop top-level read-model names."""
     project_client = MagicMock()

python/packages/foundry/tests/foundry/test_foundry_memory_provider.py

@@ -7,8 +7,9 @@ import os
 from unittest.mock import AsyncMock, Mock, patch
 
 import pytest
-from agent_framework import AGENT_FRAMEWORK_USER_AGENT, AgentResponse, Message
+from agent_framework import AgentResponse, Message
 from agent_framework._sessions import AgentSession, SessionContext
+from agent_framework._telemetry import get_user_agent
 
 from agent_framework_foundry._memory_provider import FoundryMemoryProvider
 
@@ -94,7 +95,7 @@ def test_init_with_project_endpoint_and_credential(mock_project_client: AsyncMoc
             endpoint="https://test.project.endpoint",
             credential=mock_credential,
             allow_preview=True,
-            user_agent=AGENT_FRAMEWORK_USER_AGENT,
+            user_agent=get_user_agent(),
         )
 
 

python/packages/foundry_hosting/agent_framework_foundry_hosting/_invocations.py

@@ -1,7 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.
 
 from agent_framework import AgentSession, BaseAgent, SupportsAgentRun
-from agent_framework._telemetry import user_agent_prefix
 from azure.ai.agentserver.invocations import InvocationAgentServerHost
 from starlette.requests import Request
 from starlette.responses import JSONResponse, Response, StreamingResponse
@@ -11,8 +10,6 @@ from typing_extensions import Any, AsyncGenerator
 class InvocationsHostServer(InvocationAgentServerHost):
     """An invocations server host for an agent."""
 
-    USER_AGENT_PREFIX = "foundry-hosting"
-
     def __init__(
         self,
         agent: BaseAgent,
@@ -42,11 +39,6 @@ class InvocationsHostServer(InvocationAgentServerHost):
 
     async def _handle_invoke(self, request: Request) -> Response:
         """Invoke the agent with the given request."""
-        with user_agent_prefix(self.USER_AGENT_PREFIX):
-            return await self._handle_invoke_inner(request)
-
-    async def _handle_invoke_inner(self, request: Request) -> Response:
-        """Core invoke handler logic."""
         data = await request.json()
         session_id: str = request.state.session_id
 

python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py

@@ -20,7 +20,6 @@ from agent_framework import (
     SupportsAgentRun,
     WorkflowAgent,
 )
-from agent_framework._telemetry import user_agent_prefix
 from azure.ai.agentserver.responses import (
     ResponseContext,
     ResponseEventStream,
@@ -90,7 +89,6 @@ logger = logging.getLogger(__name__)
 class ResponsesHostServer(ResponsesAgentServerHost):
     """A responses server host for an agent."""
 
-    USER_AGENT_PREFIX = "foundry-hosting"
     # TODO(@taochen): Allow a different checkpoint storage that stores checkpoints externally
     CHECKPOINT_STORAGE_PATH = "/.checkpoints"
 
@@ -150,37 +148,32 @@ class ResponsesHostServer(ResponsesAgentServerHost):
             self._is_workflow_agent = True
 
         self._agent = agent
-        self.response_handler(self._handler)  # pyright: ignore[reportUnknownMemberType]
+        self.response_handler(self._handle_response)  # pyright: ignore[reportUnknownMemberType]
 
     @staticmethod
     def _is_streaming_request(request: CreateResponse) -> bool:
         """Check if the request is a streaming request."""
         return request.stream is not None and request.stream is True
 
-    async def _handler(
+    def _handle_response(
         self,
         request: CreateResponse,
         context: ResponseContext,
         cancellation_signal: asyncio.Event,
     ) -> AsyncIterable[ResponseStreamEvent | dict[str, Any]]:
         """Handle the creation of a response."""
-        with user_agent_prefix(self.USER_AGENT_PREFIX):
-            async for event in self._handle_inner(request, context, cancellation_signal):
-                yield event
+        if self._is_workflow_agent:
+            # Workflow agents are handled differently because they require checkpoint restoration
+            return self._handle_workflow_agent(request, context)
 
-    async def _handle_inner(
+        return self._handle_regular_agent(request, context)
+
+    async def _handle_regular_agent(
         self,
         request: CreateResponse,
         context: ResponseContext,
-        cancellation_signal: asyncio.Event,
     ) -> AsyncIterable[ResponseStreamEvent | dict[str, Any]]:
-        """Core handler logic."""
-        if self._is_workflow_agent:
-            # Workflow agents are handled differently because they require checkpoint restoration
-            async for event in self._handle_workflow_agent(request, context, cancellation_signal):
-                yield event
-            return
-
+        """Handle the creation of a response for a regular (non-workflow) agent."""
         input_text = await context.get_input_text()
         history = await context.get_history()
         messages: list[str | Content | Message] = [*_to_messages(history), input_text]
@@ -243,7 +236,6 @@ class ResponsesHostServer(ResponsesAgentServerHost):
         self,
         request: CreateResponse,
         context: ResponseContext,
-        cancellation_signal: asyncio.Event,
     ) -> AsyncIterable[ResponseStreamEvent | dict[str, Any]]:
         """Handle the creation of a response for a workflow agent.
 

python/packages/foundry_hosting/pyproject.toml

@@ -4,7 +4,7 @@ description = "Foundry Hosting integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -12,7 +12,7 @@ urls.release_notes = "https://github.com/microsoft/agent-framework/releases?q=ta
 urls.issues = "https://github.com/microsoft/agent-framework/issues"
 classifiers = [
   "License :: OSI Approved :: MIT License",
-  "Development Status :: 4 - Alpha",
+  "Development Status :: 3 - Alpha",
   "Intended Audience :: Developers",
   "Programming Language :: Python :: 3",
   "Programming Language :: Python :: 3.10",
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "azure-ai-agentserver-core==2.0.0b2",
     "azure-ai-agentserver-responses==1.0.0b4",
     "azure-ai-agentserver-invocations==1.0.0b2",

python/packages/foundry_local/pyproject.toml

@@ -4,7 +4,7 @@ description = "Foundry Local integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "agent-framework-openai>=1.1.0,<2",
     "foundry-local-sdk>=0.5.1,<0.5.2",
 ]

python/packages/gemini/agent_framework_gemini/_chat_client.py

@@ -10,7 +10,6 @@ from typing import Any, ClassVar, Generic, cast
 from uuid import uuid4
 
 from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
     BaseChatClient,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
@@ -28,6 +27,7 @@ from agent_framework import (
     validate_tool_mode,
 )
 from agent_framework._settings import SecretString, load_settings
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import ChatTelemetryLayer
 from google import genai
 from google.auth.credentials import Credentials
@@ -355,7 +355,7 @@ class RawGeminiChatClient(
             )
 
             client_kwargs: dict[str, Any] = {
-                "http_options": {"headers": {"x-goog-api-client": AGENT_FRAMEWORK_USER_AGENT}},
+                "http_options": {"headers": {"x-goog-api-client": get_user_agent()}},
             }
             if configured_vertexai is not None:
                 client_kwargs["vertexai"] = configured_vertexai

python/packages/gemini/pyproject.toml

@@ -4,7 +4,7 @@ description = "Google Gemini integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2.0",
+    "agent-framework-core>=1.1.1,<2.0",
     "google-genai>=1.0.0,<2.0.0",
 ]
 

python/packages/github_copilot/pyproject.toml

@@ -4,7 +4,7 @@ description = "GitHub Copilot integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "github-copilot-sdk>=0.2.1,<=0.2.1; python_version >= '3.11'",
 ]
 

python/packages/hyperlight/README.md

@@ -130,3 +130,9 @@ codeact = HyperlightCodeActProvider(
 - `allowed_domains` accepts a single string target such as `"github.com"` to
   allow all backend-supported methods, an explicit `(target, method_or_methods)`
   tuple such as `("github.com", "GET")`, or an `AllowedDomain` named tuple.
+- Tools registered with the sandbox return their native Python value
+  (`dict`, `list`, primitives, or custom objects) directly to the guest via the
+  Hyperlight FFI. Any `result_parser` configured on a `FunctionTool` is
+  intended for LLM-facing consumers and does not run on the sandbox path —
+  apply formatting inside the tool function itself if you need it for
+  in-sandbox consumers.

python/packages/hyperlight/agent_framework_hyperlight/_execute_code_tool.py

@@ -2,42 +2,45 @@
 
 from __future__ import annotations
 
-import ast
 import asyncio
-import copy
 import mimetypes
 import shutil
 import threading
 import time
 from collections.abc import Callable, Sequence
-from dataclasses import dataclass
+from concurrent.futures import Future, ThreadPoolExecutor
+from contextlib import suppress
+from copy import copy
+from dataclasses import dataclass, field
 from pathlib import Path, PurePosixPath
 from tempfile import TemporaryDirectory
-from typing import Annotated, Any, Protocol, TypeGuard, cast
+from typing import Any, Protocol, TypeGuard, TypeVar, cast
 from urllib.parse import urlparse
 
 from agent_framework import Content, FunctionTool
 from agent_framework._tools import ApprovalMode, normalize_tools
-from pydantic import BaseModel, Field
 
 from ._instructions import build_codeact_instructions, build_execute_code_description
 from ._types import AllowedDomain, AllowedDomainInput, FileMount, FileMountHostPath, FileMountInput
 
 DEFAULT_HYPERLIGHT_BACKEND = "wasm"
 DEFAULT_HYPERLIGHT_MODULE = "python_guest.path"
-EXECUTE_CODE_INPUT_DESCRIPTION = "Python code to execute in an isolated Hyperlight sandbox."
+EXECUTE_CODE_TOOL_DESCRIPTION = "Execute Python in an isolated Hyperlight sandbox."
 OUTPUT_FILE_RETRY_ATTEMPTS = 10
 OUTPUT_FILE_RETRY_DELAY_SECONDS = 0.1
 
-
-class _ExecuteCodeInput(BaseModel):
-    code: Annotated[str, Field(description=EXECUTE_CODE_INPUT_DESCRIPTION)]
-
-
-@dataclass(frozen=True, slots=True)
-class _StoredFileMount:
-    host_path: Path
-    mount_path: str
+EXECUTE_CODE_INPUT_SCHEMA: dict[str, Any] = {
+    "type": "object",
+    "title": "_ExecuteCodeInput",
+    "properties": {
+        "code": {
+            "type": "string",
+            "title": "Code",
+            "description": "Python code to execute in an isolated Hyperlight sandbox.",
+        },
+    },
+    "required": ["code"],
+}
 
 
 @dataclass(frozen=True, slots=True)
@@ -85,13 +88,43 @@ class SandboxRuntime(Protocol):
     def execute(self, *, config: _RunConfig, code: str) -> list[Content]: ...
 
 
+_T = TypeVar("_T")
+
+
+class _SandboxWorker:
+    """Single-threaded executor that confines all sandbox operations to one OS thread.
+
+    The Hyperlight ``WasmSandbox`` is declared ``unsendable`` in PyO3, meaning it can only be
+    accessed from the OS thread that created it; touching it from any other thread triggers a
+    Rust panic that cannot be caught from Python. Every cached :class:`_SandboxEntry` therefore
+    owns its own ``_SandboxWorker``, and *all* lifecycle and execution calls against the
+    underlying sandbox object must be routed through :meth:`submit`/:meth:`run`.
+    """
+
+    __slots__ = ("_executor",)
+
+    def __init__(self, *, name: str = "hl-sandbox") -> None:
+        self._executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix=name)
+
+    def submit(self, fn: Callable[..., _T], /, *args: Any, **kwargs: Any) -> Future[_T]:
+        return self._executor.submit(fn, *args, **kwargs)
+
+    def run(self, fn: Callable[..., _T], /, *args: Any, **kwargs: Any) -> _T:
+        return self._executor.submit(fn, *args, **kwargs).result()
+
+    def shutdown(self) -> None:
+        # Do not block on shutdown; stop accepting new tasks, but allow the currently running
+        # task and any already-queued tasks to finish before the worker thread exits.
+        self._executor.shutdown(wait=False, cancel_futures=False)
+
+
 @dataclass
 class _SandboxEntry:
     sandbox: Any
     snapshot: Any
     input_dir: TemporaryDirectory[str] | None
     output_dir: TemporaryDirectory[str] | None
-    lock: threading.RLock
+    worker: _SandboxWorker = field(default_factory=_SandboxWorker)
 
 
 def _load_sandbox_class() -> type[Any]:
@@ -106,10 +139,6 @@ def _load_sandbox_class() -> type[Any]:
     return Sandbox
 
 
-def _passthrough_result_parser(result: Any) -> str:
-    return repr(result)
-
-
 def _collect_tools(*tool_groups: Any) -> list[FunctionTool]:
     tools_by_name: dict[str, FunctionTool] = {}
 
@@ -166,7 +195,7 @@ def _is_file_mount_pair(value: Any) -> TypeGuard[FileMount | tuple[FileMountHost
     return isinstance(host_path, (str, Path)) and isinstance(mount_path, str)
 
 
-def _normalize_file_mount_input(file_mount: FileMountInput) -> _StoredFileMount:
+def _normalize_file_mount_input(file_mount: FileMountInput) -> FileMount:
     host_path: FileMountHostPath
     mount_path: str
     if isinstance(file_mount, str):
@@ -176,7 +205,7 @@ def _normalize_file_mount_input(file_mount: FileMountInput) -> _StoredFileMount:
         host_path = file_mount[0]
         mount_path = file_mount[1]
 
-    return _StoredFileMount(
+    return FileMount(
         host_path=_resolve_existing_path(host_path),
         mount_path=_normalize_mount_path(mount_path),
     )
@@ -445,18 +474,13 @@ def _build_execution_contents(
 
 
 def _make_sandbox_callback(tool_obj: FunctionTool) -> Callable[..., Any]:
-    sandbox_tool = copy.copy(tool_obj)
-    # Auto-assign a passthrough parser so the raw return value round-trips through
-    # `ast.literal_eval` in the sandbox callback below. User-supplied parsers are
-    # left in place so callers can customize how results are exposed to the guest.
-    if sandbox_tool.result_parser is None:
-        sandbox_tool.result_parser = _passthrough_result_parser
+    sandbox_tool = copy(tool_obj)
 
     def _callback(**kwargs: Any) -> Any:
-        async def _invoke() -> list[Content]:
-            return await sandbox_tool.invoke(arguments=kwargs)
+        async def _invoke() -> Any:
+            return await sandbox_tool.invoke(arguments=kwargs, skip_parsing=True)
 
-        # FunctionTool.invoke() is always async. The real Hyperlight backend invokes
+        # FunctionTool.invoke() is async. The real Hyperlight backend invokes
         # registered callbacks synchronously via FFI, so this must be a sync function.
         # We run the async call on a dedicated thread to avoid conflicts with any
         # event loop that may be running on the current thread.
@@ -474,22 +498,11 @@ def _make_sandbox_callback(tool_obj: FunctionTool) -> Callable[..., Any]:
         worker.join()
         if error_box:
             raise error_box[0]
-        contents: list[Content] = result_box[0]
-
-        values: list[Any] = []
-        for content in contents:
-            if content.type == "text" and content.text is not None:
-                try:
-                    values.append(ast.literal_eval(content.text))
-                except (SyntaxError, ValueError):
-                    values.append(content.text)
-                continue
-
-            values.append(content.to_dict())
-
-        if len(values) == 1:
-            return values[0]
-        return values
+        # Return the raw value. The Hyperlight FFI marshals primitives (dict, list,
+        # str, int, float, bool, None) natively into the guest, and falls back to
+        # repr()/str() for unsupported types — so the guest receives real Python
+        # objects without a lossy host-side serialization round-trip.
+        return result_box[0]
 
     return _callback
 
@@ -509,7 +522,7 @@ def _clear_directory(output_dir: TemporaryDirectory[str] | None) -> None:
             pass
 
 
-class _SandboxRegistry:
+class _SandboxRegistry(SandboxRuntime):
     def __init__(self) -> None:
         self._entries: dict[tuple[Any, ...], _SandboxEntry] = {}
         self._entries_lock = threading.RLock()
@@ -517,28 +530,54 @@ class _SandboxRegistry:
     def execute(self, *, config: _RunConfig, code: str) -> list[Content]:
         """Execute code in a cached sandbox matching the given config.
 
-        Entries are keyed by ``config.cache_key()``. Concurrent calls with the same
-        key are serialized by the entry lock so they never race, but they share the
-        same sandbox instance. For true parallel execution, use distinct provider
-        instances or configs that produce different cache keys.
+        Entries are keyed by ``config.cache_key()``. All operations against the underlying
+        sandbox object are routed through the entry's dedicated single-threaded worker, which
+        both serializes concurrent callers and satisfies the PyO3 ``unsendable`` invariant
+        that the sandbox can only be touched from the thread that created it.
         """
+        entry = self._get_or_create_entry(config)
+        return entry.worker.run(self._run_on_worker, entry, code)
+
+    @staticmethod
+    def _run_on_worker(entry: _SandboxEntry, code: str) -> list[Content]:
+        entry.sandbox.restore(entry.snapshot)
+        _clear_directory(entry.output_dir)
+        result = entry.sandbox.run(code=code)
+        return _build_execution_contents(
+            result=result,
+            sandbox=entry.sandbox,
+            output_dir=entry.output_dir,
+            code=code,
+        )
+
+    def _get_or_create_entry(self, config: _RunConfig) -> _SandboxEntry:
         cache_key = config.cache_key()
         with self._entries_lock:
             entry = self._entries.get(cache_key)
             if entry is None:
                 entry = self._create_entry(config)
                 self._entries[cache_key] = entry
+            return entry
 
-        with entry.lock:
-            entry.sandbox.restore(entry.snapshot)
-            _clear_directory(entry.output_dir)
-            result = entry.sandbox.run(code=code)
-            return _build_execution_contents(
-                result=result,
-                sandbox=entry.sandbox,
-                output_dir=entry.output_dir,
-                code=code,
-            )
+    def close(self) -> None:
+        """Shut down all per-entry worker threads and release per-entry resources.
+
+        Safe to call multiple times. Runs any sandbox close hook on the entry's
+        own worker thread to honor the PyO3 ``unsendable`` invariant.
+        """
+        with self._entries_lock:
+            entries = list(self._entries.values())
+            self._entries.clear()
+        for entry in entries:
+            close_hook = getattr(entry.sandbox, "close", None) or getattr(entry.sandbox, "shutdown", None)
+            if callable(close_hook):
+                with suppress(Exception):
+                    entry.worker.run(close_hook)
+            entry.worker.shutdown()
+            for tmp_dir in (entry.input_dir, entry.output_dir):
+                if tmp_dir is not None:
+                    with suppress(Exception):
+                        tmp_dir.cleanup()
 
     def _create_entry(self, config: _RunConfig) -> _SandboxEntry:
         input_dir_handle = TemporaryDirectory() if config.filesystem_enabled else None
@@ -578,26 +617,37 @@ class _SandboxRegistry:
                         methods=list(allowed_domain.methods) if allowed_domain.methods is not None else None,
                     )
 
-        sandbox = _create_sandbox()
-        _configure_sandbox(sandbox=sandbox, expand_missing_scheme=False)
+        worker = _SandboxWorker()
+
+        def _build_sandbox() -> tuple[Any, Any]:
+            sandbox = _create_sandbox()
+            _configure_sandbox(sandbox=sandbox, expand_missing_scheme=False)
+
+            try:
+                sandbox.run("None")
+            except RuntimeError as exc:
+                if not _should_retry_allowed_domain_registration(error=exc, allowed_domains=config.allowed_domains):
+                    raise
+
+                sandbox = _create_sandbox()
+                _configure_sandbox(sandbox=sandbox, expand_missing_scheme=True)
+                sandbox.run("None")
+
+            snapshot = sandbox.snapshot()
+            return sandbox, snapshot
 
         try:
-            sandbox.run("None")
-        except RuntimeError as exc:
-            if not _should_retry_allowed_domain_registration(error=exc, allowed_domains=config.allowed_domains):
-                raise
+            sandbox, snapshot = worker.run(_build_sandbox)
+        except BaseException:
+            worker.shutdown()
+            raise
 
-            sandbox = _create_sandbox()
-            _configure_sandbox(sandbox=sandbox, expand_missing_scheme=True)
-            sandbox.run("None")
-
-        snapshot = sandbox.snapshot()
         return _SandboxEntry(
             sandbox=sandbox,
             snapshot=snapshot,
             input_dir=input_dir_handle,
             output_dir=output_dir_handle,
-            lock=threading.RLock(),
+            worker=worker,
         )
 
 
@@ -619,10 +669,10 @@ class HyperlightExecuteCodeTool(FunctionTool):
     ) -> None:
         super().__init__(
             name="execute_code",
-            description=EXECUTE_CODE_INPUT_DESCRIPTION,
+            description=EXECUTE_CODE_TOOL_DESCRIPTION,
             approval_mode="never_require",
             func=self._run_code,
-            input_model=_ExecuteCodeInput,
+            input_model=EXECUTE_CODE_INPUT_SCHEMA,
         )
         self._state_lock = threading.RLock()
         self._registry = _registry or _SandboxRegistry()
@@ -632,7 +682,7 @@ class HyperlightExecuteCodeTool(FunctionTool):
         self._module: str | None = module
         self._module_path: str | None = module_path
         self._managed_tools: list[FunctionTool] = []
-        self._file_mounts: dict[str, _StoredFileMount] = {}
+        self._file_mounts: dict[str, FileMount] = {}
         self._allowed_domains: dict[str, AllowedDomain] = {}
 
         if tools is not None:
@@ -648,7 +698,7 @@ class HyperlightExecuteCodeTool(FunctionTool):
     def description(self) -> str:
         state_lock = getattr(self, "_state_lock", None)
         if state_lock is None:
-            return str(self.__dict__.get("description", EXECUTE_CODE_INPUT_DESCRIPTION))
+            return str(self.__dict__.get("description", EXECUTE_CODE_TOOL_DESCRIPTION))
 
         with state_lock:
             allowed_domains = sorted(self._allowed_domains.values(), key=lambda value: value.target)
@@ -841,9 +891,9 @@ class HyperlightExecuteCodeTool(FunctionTool):
         workspace_signature = _path_tree_signature(workspace_root) if workspace_root is not None else ()
         normalized_mounts = tuple(
             _NormalizedFileMount(
-                host_path=mount.host_path,
+                host_path=Path(mount.host_path),
                 mount_path=mount.mount_path,
-                path_signature=_path_tree_signature(mount.host_path),
+                path_signature=_path_tree_signature(Path(mount.host_path)),
             )
             for mount in stored_mounts
         )

python/packages/hyperlight/pyproject.toml

@@ -4,7 +4,7 @@ description = "Hyperlight CodeAct integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "hyperlight-sandbox>=0.3.0,<0.4",
     "hyperlight-sandbox-backend-wasm>=0.3.0,<0.4 ; ((sys_platform == 'linux' and platform_machine == 'x86_64') or (sys_platform == 'win32' and platform_machine == 'AMD64')) and python_version < '3.14'",
     "hyperlight-sandbox-python-guest>=0.3.0,<0.4",

python/packages/hyperlight/tests/hyperlight/test_hyperlight_codeact.py

@@ -937,3 +937,191 @@ async def test_run_code_does_not_block_event_loop() -> None:
 
     assert concurrent_ran, "Event loop was blocked during sandbox execution"
     assert result[0].type == "text"
+
+
+class _ThreadAffinityFakeSandbox(_FakeSandbox):
+    """Fake sandbox that records the OS thread of every method invocation.
+
+    Mirrors the PyO3 ``unsendable`` invariant of ``hyperlight_sandbox.WasmSandbox``:
+    if ``__init__``, ``register_tool``, ``allow_domain``, ``run``, ``snapshot`` or ``restore``
+    are ever called from more than one thread for a given instance, the test fails.
+    """
+
+    affinity_failures: list[str] = []
+
+    def __init__(self, **kwargs: Any) -> None:
+        super().__init__(**kwargs)
+        self._owner_thread = threading.get_ident()
+        self.thread_ids: set[int] = {self._owner_thread}
+
+    def _record(self, method: str) -> None:
+        ident = threading.get_ident()
+        self.thread_ids.add(ident)
+        if ident != self._owner_thread:
+            _ThreadAffinityFakeSandbox.affinity_failures.append(
+                f"{method} called from thread {ident}, expected {self._owner_thread}"
+            )
+
+    def register_tool(self, name_or_tool: Any, callback: Any | None = None) -> None:
+        self._record("register_tool")
+        super().register_tool(name_or_tool, callback)
+
+    def allow_domain(self, target: str, methods: list[str] | None = None) -> None:
+        self._record("allow_domain")
+        super().allow_domain(target, methods)
+
+    def run(self, code: str) -> _FakeResult:
+        self._record("run")
+        return super().run(code)
+
+    def snapshot(self) -> str:
+        self._record("snapshot")
+        return super().snapshot()
+
+    def restore(self, snapshot: Any) -> None:
+        self._record("restore")
+        super().restore(snapshot)
+
+
+async def test_sandbox_calls_are_pinned_to_owning_worker_thread(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Regression: WasmSandbox is unsendable; every sandbox call must run on its owner thread."""
+    _ThreadAffinityFakeSandbox.instances.clear()
+    _ThreadAffinityFakeSandbox.affinity_failures.clear()
+    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ThreadAffinityFakeSandbox)
+
+    execute_code = HyperlightExecuteCodeTool()
+
+    # Invoke many times concurrently; asyncio.to_thread will spread these across the default
+    # executor's worker threads, which previously caused PyO3 to panic when a different thread
+    # touched the cached sandbox.
+    results = await asyncio.gather(*[execute_code.invoke(arguments={"code": "None"}) for _ in range(8)])
+    for result in results:
+        assert result[0].type == "text"
+
+    assert _ThreadAffinityFakeSandbox.affinity_failures == []
+    assert len(_ThreadAffinityFakeSandbox.instances) == 1
+    sandbox = _ThreadAffinityFakeSandbox.instances[0]
+    # All sandbox-touching calls must have stayed on a single owning thread, distinct from the
+    # caller thread that asyncio.to_thread used for dispatch.
+    assert sandbox.thread_ids == {sandbox._owner_thread}
+    assert sandbox._owner_thread != threading.get_ident()
+
+
+async def test_sandbox_owner_thread_persists_across_dispatch_threads(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Sequential calls landing on different dispatch threads still share one sandbox thread."""
+    _ThreadAffinityFakeSandbox.instances.clear()
+    _ThreadAffinityFakeSandbox.affinity_failures.clear()
+    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ThreadAffinityFakeSandbox)
+
+    execute_code = HyperlightExecuteCodeTool()
+
+    for _ in range(5):
+        result = await execute_code.invoke(arguments={"code": "None"})
+        assert result[0].type == "text"
+
+    assert _ThreadAffinityFakeSandbox.affinity_failures == []
+    assert len(_ThreadAffinityFakeSandbox.instances) == 1
+
+
+def test_sandbox_registry_close_shuts_down_workers(monkeypatch: pytest.MonkeyPatch) -> None:
+    _FakeSandbox.instances.clear()
+    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _FakeSandbox)
+
+    registry = execute_code_module._SandboxRegistry()
+    execute_code = HyperlightExecuteCodeTool(_registry=registry)
+    asyncio.run(execute_code.invoke(arguments={"code": "None"}))
+
+    entries = list(registry._entries.values())
+    assert len(entries) == 1
+    worker = entries[0].worker
+
+    registry.close()
+
+    assert registry._entries == {}
+    # Submitting after shutdown must fail; this proves the executor was actually torn down.
+    with pytest.raises(RuntimeError):
+        worker.submit(lambda: None)
+
+
+def test_sandbox_registry_close_releases_per_entry_resources(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
+    """close() must invoke any sandbox close hook and release temp directories."""
+
+    close_calls: list[int] = []
+
+    class _ClosableFakeSandbox(_FakeSandbox):
+        def close(self) -> None:
+            close_calls.append(1)
+
+    _FakeSandbox.instances.clear()
+    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ClosableFakeSandbox)
+
+    workspace = tmp_path / "workspace"
+    workspace.mkdir()
+    registry = execute_code_module._SandboxRegistry()
+    execute_code = HyperlightExecuteCodeTool(workspace_root=workspace, _registry=registry)
+    asyncio.run(execute_code.invoke(arguments={"code": "None"}))
+
+    entries = list(registry._entries.values())
+    assert len(entries) == 1
+    entry = entries[0]
+    assert entry.input_dir is not None and entry.output_dir is not None
+    input_path = Path(entry.input_dir.name)
+    output_path = Path(entry.output_dir.name)
+    assert input_path.exists() and output_path.exists()
+
+    registry.close()
+
+    assert close_calls == [1]
+    assert not input_path.exists()
+    assert not output_path.exists()
+
+
+async def test_make_sandbox_callback_returns_native_dict() -> None:
+    """Host tool returning a dict must be forwarded as a native dict (no repr round-trip)."""
+
+    @tool
+    def get_weather(city: str) -> dict[str, Any]:
+        """Get weather."""
+        return {"city": city, "temp_c": 21.5}
+
+    callback = execute_code_module._make_sandbox_callback(get_weather)
+    result = callback(city="Seattle")
+
+    assert isinstance(result, dict)
+    assert result == {"city": "Seattle", "temp_c": 21.5}
+
+
+async def test_make_sandbox_callback_bypasses_user_result_parser() -> None:
+    """Documented behavior change: result_parser is bypassed in the sandbox path."""
+
+    parser_calls: list[Any] = []
+
+    def parser(value: Any) -> str:
+        parser_calls.append(value)
+        return "PARSED"
+
+    @tool(result_parser=parser)
+    def make_payload() -> dict[str, int]:
+        """Returns a dict."""
+        return {"a": 1, "b": 2}
+
+    callback = execute_code_module._make_sandbox_callback(make_payload)
+    result = callback()
+
+    assert result == {"a": 1, "b": 2}
+    assert parser_calls == [], "result_parser must not run on the sandbox path"
+
+
+async def test_make_sandbox_callback_propagates_exceptions() -> None:
+    @tool
+    def boom(x: int) -> int:
+        """Always fails."""
+        raise RuntimeError("nope")
+
+    callback = execute_code_module._make_sandbox_callback(boom)
+    with pytest.raises(RuntimeError, match="nope"):
+        callback(x=1)

python/packages/lab/pyproject.toml

@@ -4,7 +4,7 @@ description = "Experimental modules for Microsoft Agent Framework"
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Programming Language :: Python :: 3.14",
 ]
 dependencies = [
-  "agent-framework-core>=1.1.0,<2",
+  "agent-framework-core>=1.1.1,<2",
 ]
 
 [project.optional-dependencies]

python/packages/mem0/pyproject.toml

@@ -4,7 +4,7 @@ description = "Mem0 integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "mem0ai>=1.0.0,<2",
 ]
 

python/packages/ollama/pyproject.toml

@@ -4,7 +4,7 @@ description = "Ollama integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://learn.microsoft.com/en-us/agent-framework/"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "ollama>=0.5.3,<0.5.4",
 ]
 

python/packages/openai/pyproject.toml

@@ -4,7 +4,7 @@ description = "OpenAI integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.0"
+version = "1.1.1"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "openai>=1.99.0,<3",
 ]
 

python/packages/orchestrations/pyproject.toml

@@ -4,7 +4,7 @@ description = "Orchestration patterns for Microsoft Agent Framework. Includes Se
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
 ]
 
 [tool.uv]

python/packages/purview/agent_framework_purview/_client.py

@@ -11,7 +11,7 @@ from typing import Any, Literal, TypeVar, Union, overload
 from uuid import uuid4
 
 import httpx
-from agent_framework import AGENT_FRAMEWORK_USER_AGENT
+from agent_framework._telemetry import get_user_agent
 from agent_framework.observability import get_tracer
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
@@ -189,7 +189,7 @@ class PurviewClient:
         payload = model.model_dump(by_alias=True, exclude_none=True, mode="json")
         request_headers = {
             "Authorization": f"Bearer {token}",
-            "User-Agent": AGENT_FRAMEWORK_USER_AGENT,
+            "User-Agent": get_user_agent(),
             "Content-Type": "application/json",
         }
         if correlation_id:

python/packages/purview/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Purview (Graph dataSecurityAndGovernance) integration f
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "azure-core>=1.30.0,<2",
     "httpx>=0.27.0,<0.29",
 ]

python/packages/redis/pyproject.toml

@@ -4,7 +4,7 @@ description = "Redis integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.0,<2",
+    "agent-framework-core>=1.1.1,<2",
     "redis>=6.4.0,<7.2.1",
     "redisvl>=0.11.0,<0.16",
     "numpy>=2.2.6,<3"

python/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.0"
+version = "1.1.1"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core[all]==1.1.0",
+    "agent-framework-core[all]==1.1.1",
 ]
 
 [dependency-groups]

python/samples/02-agents/providers/foundry/foundry_chat_client_with_toolbox.py

@@ -42,11 +42,12 @@ def create_sample_toolbox(name: str) -> str:
     Toolboxes are normally configured in the Foundry portal or a deployment
     script, not the application itself. This helper exists so the samples can
     be run end-to-end without first setting a toolbox up by hand — delete any
-    existing toolbox under ``name``, then create a fresh version containing a
-    single MCP tool. Returns the created version identifier.
+    existing toolbox under ``name``, then create a fresh version containing an
+    MCP tool, a web search tool, and a code interpreter tool. Returns the
+    created version identifier.
     """
     from azure.ai.projects import AIProjectClient
-    from azure.ai.projects.models import MCPTool, Tool
+    from azure.ai.projects.models import CodeInterpreterTool, MCPTool, Tool, WebSearchTool
     from azure.core.exceptions import ResourceNotFoundError
 
     with (
@@ -67,6 +68,9 @@ def create_sample_toolbox(name: str) -> str:
             )
         ]
 
+        tools.append(WebSearchTool(name="web_search"))
+        tools.append(CodeInterpreterTool(name="code_interpreter"))
+
         created = project_client.beta.toolboxes.create_version(
             name=name,
             description="Toolbox version with MCP require_approval set to 'never'.",

python/samples/04-hosting/foundry-hosted-agents/responses/02_local_tools/main.py

@@ -3,6 +3,7 @@
 import os
 import subprocess
 from random import randint
+from typing import Annotated
 
 from agent_framework import Agent, tool
 from agent_framework.foundry import FoundryChatClient
@@ -10,7 +11,6 @@ from agent_framework_foundry_hosting import ResponsesHostServer
 from azure.identity import AzureCliCredential
 from dotenv import load_dotenv
 from pydantic import Field
-from typing import Annotated
 
 # Load environment variables from .env file
 load_dotenv()

python/scripts/flaky_report/__init__.py

@@ -0,0 +1,11 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Flaky test report aggregation and trend generation.
+
+Parses JUnit XML (``pytest.xml``) files produced by each CI job, merges
+them with historical data, and generates a markdown trend report showing
+per-test status across the last N runs.
+
+Usage:
+    uv run python -m scripts.flaky_report <reports-dir> <history-file> <output-file>
+"""

python/scripts/flaky_report/__main__.py

@@ -0,0 +1,20 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""CLI entry point for the flaky test report tool.
+
+Usage:
+    uv run python -m scripts.flaky_report <reports-dir> <history-file> <output-file>
+
+Example (from python/ directory):
+    uv run python -m scripts.flaky_report \\
+        ../flaky-reports/ \\
+        flaky-report-history.json \\
+        flaky-test-report.md
+"""
+
+import sys
+
+from scripts.flaky_report.aggregate import main
+
+if __name__ == "__main__":
+    sys.exit(main())

python/scripts/flaky_report/aggregate.py

@@ -0,0 +1,396 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Aggregate per-provider JUnit XML test results and generate a trend report.
+
+Parses ``pytest.xml`` (JUnit XML) files produced by each CI job, merges them
+into a single run, combines with historical data, and generates a markdown
+trend table — the same pattern used by ``scripts/sample_validation/aggregate.py``.
+
+Usage (from CI):
+    python aggregate.py <reports-dir> <history-file> <output-file>
+
+The reports directory is expected to contain subdirectories named
+``test-results-<provider>/`` each containing a ``pytest.xml`` file
+(created by ``actions/download-artifact``).
+"""
+
+from __future__ import annotations
+
+import json
+import sys
+import xml.etree.ElementTree as ET
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+MAX_HISTORY = 5
+
+STATUS_EMOJI = {
+    "passed": "✅",
+    "failed": "❌",
+    "skipped": "⏭️",
+    "xfailed": "⚠️",
+    "error": "❌",
+}
+
+
+def _format_run_label(timestamp: str) -> str:
+    """Format a timestamp as a compact column label (e.g. '04-16 00:57')."""
+    try:
+        dt = datetime.fromisoformat(timestamp)
+        return dt.strftime("%m-%d %H:%M")
+    except (ValueError, TypeError):
+        return timestamp[:16]
+
+
+def _derive_provider(directory_name: str) -> str:
+    """Derive a provider label from a report directory name.
+
+    ``test-results-openai`` → ``OpenAI``
+    ``test-results-azure-openai`` → ``Azure OpenAI``
+    """
+    raw = directory_name.replace("test-results-", "")
+    known = {
+        "openai": "OpenAI",
+        "azure-openai": "Azure OpenAI",
+        "misc": "Misc (Anthropic, Ollama, MCP)",
+        "functions": "Functions",
+        "foundry": "Foundry",
+        "cosmos": "Cosmos",
+        "unit": "Unit",
+    }
+    if raw in known:
+        return known[raw]
+    parts = raw.split("-")
+    return " ".join(p.capitalize() for p in parts)
+
+
+def _parse_junit_xml(xml_path: Path) -> list[dict[str, str]]:
+    """Parse a JUnit XML file and return a list of test result dicts.
+
+    Each dict has keys: ``nodeid``, ``status``, ``duration``, ``message``.
+    """
+    results: list[dict[str, str]] = []
+    try:
+        tree = ET.parse(xml_path)  # noqa: S314
+    except ET.ParseError as exc:
+        print(f"Warning: failed to parse JUnit XML report '{xml_path}': {exc}", file=sys.stderr)
+        return results
+    root = tree.getroot()
+
+    # Handle both <testsuites><testsuite>... and <testsuite>... layouts
+    testcases: list[ET.Element] = []
+    if root.tag == "testsuites":
+        for suite in root.findall("testsuite"):
+            testcases.extend(suite.findall("testcase"))
+    elif root.tag == "testsuite":
+        testcases = list(root.findall("testcase"))
+
+    for tc in testcases:
+        classname = tc.get("classname", "")
+        name = tc.get("name", "")
+        duration = tc.get("time", "0")
+
+        # Use classname::name as a stable identifier.
+        # pytest writes classname as the dotted module path (possibly including
+        # a test class), e.g. "packages.openai.tests.openai.test_chat_client"
+        # or "packages.openai.tests.openai.test_chat_client.TestClass".
+        nodeid = f"{classname}::{name}" if classname else name
+
+        # Extract module/file name from classname for display context.
+        # pytest writes classname as a dotted path. For tests inside a class
+        # it appends the class name, e.g.:
+        #   "packages.foundry.tests.foundry.test_foundry_embedding_client.TestFoundryEmbeddingIntegration"
+        # We want the file-level module: "test_foundry_embedding_client"
+        if classname:
+            parts = classname.rsplit(".", 2)
+            # If the last segment starts with uppercase it's a class name — take the one before it
+            if len(parts) >= 2 and parts[-1][0:1].isupper():
+                module = parts[-2]
+            else:
+                module = parts[-1]
+        else:
+            module = ""
+
+        # Determine status from child elements
+        failure = tc.find("failure")
+        error = tc.find("error")
+        skipped = tc.find("skipped")
+
+        if failure is not None:
+            status = "failed"
+            message = failure.get("message", "")
+        elif error is not None:
+            status = "error"
+            message = error.get("message", "")
+        elif skipped is not None:
+            # pytest marks xfail as <skipped type="pytest.xfail">
+            skip_type = skipped.get("type", "")
+            status = "xfailed" if "xfail" in skip_type else "skipped"
+            message = skipped.get("message", "")
+        else:
+            status = "passed"
+            message = ""
+
+        results.append({
+            "nodeid": nodeid,
+            "status": status,
+            "duration": duration,
+            "message": message,
+            "module": module,
+        })
+
+    return results
+
+
+# ---------------------------------------------------------------------------
+# Loading
+# ---------------------------------------------------------------------------
+
+
+def load_current_run(reports_dir: Path) -> dict[str, Any]:
+    """Load per-provider JUnit XML reports from the current CI run and merge.
+
+    Args:
+        reports_dir: Directory containing ``test-results-<provider>/`` subdirs.
+
+    Returns:
+        Merged run dict with ``timestamp``, ``summary``, ``results``.
+    """
+    combined_results: dict[str, dict[str, str]] = {}  # nodeid → {status, provider}
+
+    # actions/download-artifact creates: reports_dir/test-results-openai/pytest.xml
+    xml_files: list[tuple[str, Path]] = []
+    if reports_dir.is_dir():
+        for subdir in sorted(reports_dir.iterdir()):
+            if subdir.is_dir():
+                xml_file = subdir / "pytest.xml"
+                if xml_file.exists():
+                    xml_files.append((subdir.name, xml_file))
+
+    if not xml_files:
+        print(f"Warning: No pytest.xml files found in {reports_dir}")
+        return {
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "summary": {
+                "total": 0,
+                "passed": 0,
+                "failed": 0,
+                "skipped": 0,
+            },
+            "results": {},
+        }
+
+    for dir_name, xml_file in xml_files:
+        print(f"  Loading: {xml_file}")
+        provider = _derive_provider(dir_name)
+        tests = _parse_junit_xml(xml_file)
+        for test in tests:
+            combined_results[test["nodeid"]] = {
+                "status": test["status"],
+                "provider": provider,
+                "module": test.get("module", ""),
+            }
+
+    # Build summary counts using mutually exclusive status buckets.
+    # Errors are folded into the failed count for display purposes.
+    statuses = [r["status"] for r in combined_results.values()]
+    summary = {
+        "total": len(statuses),
+        "passed": statuses.count("passed"),
+        "failed": statuses.count("failed") + statuses.count("error"),
+        "skipped": statuses.count("skipped"),
+    }
+
+    return {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "summary": summary,
+        "results": combined_results,
+    }
+
+
+def load_history(history_path: Path) -> list[dict[str, Any]]:
+    """Load previous run history from a cache file."""
+    if history_path.exists():
+        with open(history_path, encoding="utf-8") as f:
+            data = json.load(f)
+        runs = data.get("runs", [])
+        print(f"  Loaded {len(runs)} previous run(s) from history")
+        return runs
+    print("  No previous history found")
+    return []
+
+
+def save_history(history_path: Path, runs: list[dict[str, Any]]) -> None:
+    """Save run history, keeping only the last ``MAX_HISTORY`` entries."""
+    history_path.parent.mkdir(parents=True, exist_ok=True)
+    trimmed = runs[-MAX_HISTORY:]
+    with open(history_path, "w", encoding="utf-8") as f:
+        json.dump({"runs": trimmed}, f, indent=2)
+    print(f"  Saved {len(trimmed)} run(s) to history")
+
+
+# ---------------------------------------------------------------------------
+# Report generation
+# ---------------------------------------------------------------------------
+
+
+def _short_name(nodeid: str) -> str:
+    """Extract a short test name from a full nodeid.
+
+    ``packages.openai.tests.openai.test_openai_chat_client::test_integration_options``
+    → ``test_integration_options``
+    """
+    return nodeid.split("::")[-1] if "::" in nodeid else nodeid
+
+
+def generate_trend_report(runs: list[dict[str, Any]]) -> str:
+    """Generate a markdown trend report from run history."""
+    lines = [
+        "# 🔬 Flaky Test Report",
+        "",
+        f"*Generated: {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M UTC')}*",
+        "",
+    ]
+
+    # --- Overall status table (most recent first) ---
+    lines.append("## Overall Status (Last 5 Runs)")
+    lines.append("")
+    lines.append("| Run | Total | ✅ Passed | ❌ Failed | ⏭️ Skipped |")
+    lines.append("|-----|-------|-----------|-----------|------------|")
+
+    for run in reversed(runs):
+        s = run.get("summary", {})
+        total = s.get("total", 0)
+        label = _format_run_label(run["timestamp"])
+        lines.append(
+            f"| {label} "
+            f"| {total} "
+            f"| {s.get('passed', 0)}/{total} "
+            f"| {s.get('failed', 0)}/{total} "
+            f"| {s.get('skipped', 0)}/{total} |"
+        )
+
+    for _ in range(MAX_HISTORY - len(runs)):
+        lines.append("| N/A | N/A | N/A | N/A | N/A |")
+
+    lines.append("")
+
+    # --- Per-test results table ---
+    lines.append("## Per-Test Results")
+    lines.append("")
+
+    # Collect all test nodeids, providers, and modules across all runs
+    all_tests: dict[str, str] = {}  # nodeid → provider (from most recent run)
+    all_modules: dict[str, str] = {}  # nodeid → module (from most recent run)
+    for run in runs:
+        for nodeid, info in run.get("results", {}).items():
+            provider = info.get("provider", "Unknown") if isinstance(info, dict) else "Unknown"
+            module = info.get("module", "") if isinstance(info, dict) else ""
+            all_tests[nodeid] = provider
+            all_modules[nodeid] = module
+
+    if not all_tests:
+        lines.append("*No test results available.*")
+        return "\n".join(lines)
+
+    # Build header (most recent run first)
+    header = "| Test | File | Provider |"
+    separator = "|------|------|----------|"
+    for run in reversed(runs):
+        label = _format_run_label(run["timestamp"])
+        header += f" {label} |"
+        separator += "------------|"
+    for _ in range(MAX_HISTORY - len(runs)):
+        header += " N/A |"
+        separator += "-----|"
+
+    lines.append(header)
+    lines.append(separator)
+
+    # Sort by provider then test name
+    for nodeid in sorted(all_tests, key=lambda n: (all_tests[n], n)):
+        provider = all_tests[nodeid]
+        module = all_modules.get(nodeid, "")
+        short = _short_name(nodeid)
+        row = f"| `{short}` | `{module}` | {provider} |"
+
+        for run in reversed(runs):
+            result = run.get("results", {}).get(nodeid)
+            if result is None:
+                emoji = "N/A"
+            else:
+                status = result.get("status", "N/A") if isinstance(result, dict) else result
+                emoji = STATUS_EMOJI.get(status, "❓")
+            row += f" {emoji} |"
+
+        for _ in range(MAX_HISTORY - len(runs)):
+            row += " N/A |"
+
+        lines.append(row)
+
+    lines.append("")
+    lines.append("**Legend:** ✅ Passed · ❌ Failed · ⏭️ Skipped · ⚠️ Expected Failure (xfail) · N/A Not available")
+    lines.append("")
+
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# CLI entry point
+# ---------------------------------------------------------------------------
+
+
+def main() -> int:
+    if len(sys.argv) != 4:
+        print("Usage: python aggregate.py <reports-dir> <history-file> <output-file>")
+        return 1
+
+    reports_dir = Path(sys.argv[1])
+    history_path = Path(sys.argv[2])
+    output_path = Path(sys.argv[3])
+
+    print("Aggregating test results from JUnit XML...")
+
+    # Load current run's per-provider XML reports
+    print(f"\nLoading reports from {reports_dir}:")
+    current_run = load_current_run(reports_dir)
+    s = current_run.get("summary", {})
+    total = s.get("total", 0)
+    print(
+        f"  Current run: {s.get('passed', 0)} passed, "
+        f"{s.get('failed', 0)} failed, "
+        f"{s.get('skipped', 0)} skipped "
+        f"(total: {total})"
+    )
+
+    # Load history and append current run (skip empty runs to avoid polluting trend)
+    print(f"\nLoading history from {history_path}:")
+    runs = load_history(history_path)
+    if total > 0:
+        runs.append(current_run)
+        runs = runs[-MAX_HISTORY:]
+    else:
+        print("  Skipping history append (no test results in current run)")
+
+    # Save updated history
+    print(f"\nSaving history to {history_path}:")
+    save_history(history_path, runs)
+
+    # Generate trend report
+    print("\nGenerating trend report...")
+    report = generate_trend_report(runs)
+
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path.write_text(report, encoding="utf-8")
+    print(f"Trend report written to {output_path}")
+
+    # Print the report to stdout for CI visibility
+    print("\n" + "=" * 80)
+    print(report)
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

python/uv.lock

@@ -96,7 +96,7 @@ wheels = [
 
 [[package]]
 name = "agent-framework"
-version = "1.1.0"
+version = "1.1.1"
 source = { virtual = "." }
 dependencies = [
     { name = "agent-framework-core", extra = ["all"], marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -151,7 +151,7 @@ dev = [
 
 [[package]]
 name = "agent-framework-a2a"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/a2a" }
 dependencies = [
     { name = "a2a-sdk", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -166,7 +166,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-ag-ui"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/ag-ui" }
 dependencies = [
     { name = "ag-ui-protocol", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -194,7 +194,7 @@ provides-extras = ["dev"]
 
 [[package]]
 name = "agent-framework-anthropic"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/anthropic" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -209,7 +209,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-azure-ai-search"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/azure-ai-search" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -224,7 +224,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-azure-cosmos"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/azure-cosmos" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -239,7 +239,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-azurefunctions"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/azurefunctions" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -261,7 +261,7 @@ dev = []
 
 [[package]]
 name = "agent-framework-bedrock"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/bedrock" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -278,7 +278,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-chatkit"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/chatkit" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -293,7 +293,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-claude"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/claude" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -308,7 +308,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-copilotstudio"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/copilotstudio" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -323,7 +323,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-core"
-version = "1.1.0"
+version = "1.1.1"
 source = { editable = "packages/core" }
 dependencies = [
     { name = "opentelemetry-api", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -395,7 +395,7 @@ provides-extras = ["all"]
 
 [[package]]
 name = "agent-framework-declarative"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/declarative" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -420,7 +420,7 @@ dev = [{ name = "types-pyyaml", specifier = "==6.0.12.20250915" }]
 
 [[package]]
 name = "agent-framework-devui"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/devui" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -458,7 +458,7 @@ provides-extras = ["dev", "all"]
 
 [[package]]
 name = "agent-framework-durabletask"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/durabletask" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -485,7 +485,7 @@ dev = [{ name = "types-python-dateutil", specifier = "==2.9.0.20260402" }]
 
 [[package]]
 name = "agent-framework-foundry"
-version = "1.1.0"
+version = "1.1.1"
 source = { editable = "packages/foundry" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -504,7 +504,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-foundry-hosting"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 source = { editable = "packages/foundry_hosting" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -523,7 +523,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-foundry-local"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/foundry_local" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -540,7 +540,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-gemini"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 source = { editable = "packages/gemini" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -555,7 +555,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-github-copilot"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/github_copilot" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -570,7 +570,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-hyperlight"
-version = "1.0.0a260421"
+version = "1.0.0a260423"
 source = { editable = "packages/hyperlight" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -589,7 +589,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-lab"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/lab" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -670,7 +670,7 @@ dev = [
 
 [[package]]
 name = "agent-framework-mem0"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/mem0" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -685,7 +685,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-ollama"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/ollama" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -700,7 +700,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-openai"
-version = "1.1.0"
+version = "1.1.1"
 source = { editable = "packages/openai" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -715,7 +715,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-orchestrations"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/orchestrations" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -726,7 +726,7 @@ requires-dist = [{ name = "agent-framework-core", editable = "packages/core" }]
 
 [[package]]
 name = "agent-framework-purview"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/purview" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -743,7 +743,7 @@ requires-dist = [
 
 [[package]]
 name = "agent-framework-redis"
-version = "1.0.0b260421"
+version = "1.0.0b260423"
 source = { editable = "packages/redis" }
 dependencies = [
     { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },