Compare commits

..
1676 changed files with 32789 additions and 101451 deletions
-1
View File
@@ -3,7 +3,6 @@
"image": "mcr.microsoft.com/devcontainers/dotnet",
"features": {
"ghcr.io/devcontainers/features/azure-cli:1.2.9": {},
"ghcr.io/devcontainers/features/docker-in-docker:2": {},
"ghcr.io/devcontainers/features/github-cli:1": {
"version": "2"
},
-1
View File
@@ -20,7 +20,6 @@ ignorePatterns:
- pattern: "https://your-resource.openai.azure.com/"
- pattern: "http://host.docker.internal"
- pattern: "https://openai.github.io/openai-agents-js/openai/agents/classes/"
- pattern: "https:\/\/dotnet.microsoft.com\/download"
# excludedDirs:
# Folders which include links to localhost, since it's not ignored with regular expressions
baseUrl: https://github.com/microsoft/agent-framework/
-18
View File
@@ -8,10 +8,6 @@ inputs:
os:
description: The operating system to set up
required: true
exclude-packages:
description: Space-separated list of packages to exclude from uv sync
required: false
default: ''
runs:
using: "composite"
@@ -23,20 +19,6 @@ runs:
enable-cache: true
cache-suffix: ${{ inputs.os }}-${{ inputs.python-version }}
cache-dependency-glob: "**/uv.lock"
- name: Exclude incompatible workspace packages
if: ${{ inputs.exclude-packages != '' }}
shell: bash
run: |
for pkg in ${{ inputs.exclude-packages }}; do
for f in python/packages/*/pyproject.toml; do
if grep -q "name = \"$pkg\"" "$f"; then
pkg_dir=$(dirname "$f" | sed 's|python/||')
echo "Excluding workspace package: $pkg ($pkg_dir)"
sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
sed -i.bak '/'"$pkg"' = { workspace = true }/d' python/pyproject.toml
fi
done
done
- name: Install the project
shell: bash
run: |
@@ -24,9 +24,7 @@ runs:
using: "composite"
steps:
- name: Set up Node.js environment
uses: actions/setup-node@v6
with:
node-version: 22
uses: actions/setup-node@v4
- name: Install Copilot CLI
shell: bash
@@ -34,7 +32,7 @@ runs:
- name: Test Copilot CLI
shell: bash
run: copilot --version && copilot -p "What can you do in one sentence?"
run: copilot -p "What can you do in one sentence?"
- name: Azure CLI Login
uses: azure/login@v2
@@ -1,166 +0,0 @@
name: Setup Local MCP Server
description: Start and validate a local streamable HTTP MCP server for integration tests
inputs:
fallback_url:
description: Existing LOCAL_MCP_URL value to keep as a fallback if local startup fails
required: false
default: ''
host:
description: Host interface to bind the local MCP server
required: false
default: '127.0.0.1'
port:
description: Port to bind the local MCP server
required: false
default: '8011'
mount_path:
description: Mount path for the local streamable HTTP MCP endpoint
required: false
default: '/mcp'
outputs:
effective_url:
description: Local MCP URL when startup succeeds, otherwise the provided fallback URL
value: ${{ steps.start.outputs.effective_url }}
local_url:
description: URL of the local MCP server
value: ${{ steps.start.outputs.local_url }}
started:
description: Whether the local MCP server started and passed validation
value: ${{ steps.start.outputs.started }}
pid:
description: PID of the local MCP server process when startup succeeded
value: ${{ steps.start.outputs.pid }}
runs:
using: composite
steps:
- name: Start and validate local MCP server
id: start
shell: bash
run: |
set -euo pipefail
host="${{ inputs.host }}"
port="${{ inputs.port }}"
mount_path="${{ inputs.mount_path }}"
fallback_url="${{ inputs.fallback_url }}"
if [[ ! "$mount_path" =~ ^/ ]]; then
mount_path="/$mount_path"
fi
local_url="http://${host}:${port}${mount_path}"
health_url="http://${host}:${port}/healthz"
log_file="$RUNNER_TEMP/local-mcp-server.log"
pid_file="$RUNNER_TEMP/local-mcp-server.pid"
rm -f "$log_file" "$pid_file"
server_pid="$(
python3 - "$GITHUB_WORKSPACE/python" "$log_file" "$host" "$port" "$mount_path" <<'PY'
from __future__ import annotations
import subprocess
import sys
workspace, log_file, host, port, mount_path = sys.argv[1:]
with open(log_file, "w", encoding="utf-8") as log:
process = subprocess.Popen(
[
"uv",
"run",
"python",
"scripts/local_mcp_streamable_http_server.py",
"--host",
host,
"--port",
port,
"--mount-path",
mount_path,
],
cwd=workspace,
stdout=log,
stderr=subprocess.STDOUT,
start_new_session=True,
)
print(process.pid)
PY
)"
echo "$server_pid" > "$pid_file"
started=false
for _ in $(seq 1 30); do
if curl --silent --fail "$health_url" >/dev/null; then
started=true
break
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
break
fi
sleep 1
done
if [[ "$started" == "true" ]]; then
if ! (
cd "$GITHUB_WORKSPACE/python"
LOCAL_MCP_URL="$local_url" uv run python - <<'PY'
from __future__ import annotations
import asyncio
import os
from agent_framework import Content, MCPStreamableHTTPTool
def result_to_text(result: str | list[Content]) -> str:
if isinstance(result, str):
return result
return "\n".join(content.text for content in result if content.type == "text" and content.text)
async def main() -> None:
tool = MCPStreamableHTTPTool(
name="local_ci_mcp",
url=os.environ["LOCAL_MCP_URL"],
approval_mode="never_require",
)
async with tool:
assert tool.functions, "Local MCP server did not expose any tools."
result = result_to_text(await tool.functions[0].invoke(query="What is Agent Framework?"))
assert result, "Local MCP server returned an empty response."
asyncio.run(main())
PY
); then
started=false
fi
fi
effective_url="$local_url"
pid="$server_pid"
if [[ "$started" != "true" ]]; then
effective_url="$fallback_url"
pid=""
if kill -0 "$server_pid" 2>/dev/null; then
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" || true
sleep 1
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" || true
fi
echo "Local MCP server was unavailable; continuing with fallback LOCAL_MCP_URL."
if [[ -f "$log_file" ]]; then
tail -n 100 "$log_file" || true
fi
else
echo "Using local MCP server at $local_url"
fi
echo "started=$started" >> "$GITHUB_OUTPUT"
echo "local_url=$local_url" >> "$GITHUB_OUTPUT"
echo "effective_url=$effective_url" >> "$GITHUB_OUTPUT"
echo "pid=$pid" >> "$GITHUB_OUTPUT"
-216
View File
@@ -1,216 +0,0 @@
# Copyright (c) Microsoft. All rights reserved.
"""Scan open issues and PRs labeled 'waiting-for-author' for stale follow-ups.
Team members manually add the 'waiting-for-author' label when they need a
response from the external author. If the author hasn't replied within
DAYS_THRESHOLD days of the last team comment, post a reminder and add the
'requested-info' label to prevent duplicate pings.
"""
from __future__ import annotations
import os
import sys
import time
from datetime import datetime, timezone
from github import Auth, Github, GithubException
from github.Issue import Issue
from github.IssueComment import IssueComment
PING_COMMENT = (
"@{author}, friendly reminder — this issue is waiting on your response. "
"Please share any updates when you get a chance. (This is an automated message.)"
)
TRIGGER_LABEL = "waiting-for-author"
PINGED_LABEL = "requested-info"
def get_team_members(g: Github, org: str, team_slug: str) -> set[str]:
"""Fetch active team member usernames."""
try:
org_obj = g.get_organization(org)
team = org_obj.get_team_by_slug(team_slug)
return {m.login for m in team.get_members()}
except GithubException as exc:
if exc.status in (403, 404):
print(
f"ERROR: Failed to fetch team members for {org}/{team_slug} "
f"(HTTP {exc.status}). Check that the token has the 'read:org' "
f"scope and that the team slug '{team_slug}' is correct."
)
else:
print(f"ERROR: Failed to fetch team members for {org}/{team_slug}: {exc}")
sys.exit(1)
except Exception as exc:
print(f"ERROR: Failed to fetch team members for {org}/{team_slug}: {exc}")
sys.exit(1)
def find_last_team_comment(
comments: list[IssueComment], team_members: set[str]
) -> IssueComment | None:
"""Return the most recent comment from a team member, or None."""
for comment in reversed(comments):
if comment.user and comment.user.login in team_members:
return comment
return None
def author_replied_after(
comments: list[IssueComment], author: str, after: datetime
) -> bool:
"""Check if the issue author commented after the given timestamp."""
for comment in comments:
if (
comment.user
and comment.user.login == author
and comment.created_at > after
):
return True
return False
def should_ping(
issue: Issue,
team_members: set[str],
days_threshold: int,
now: datetime,
) -> bool:
"""Determine whether this issue/PR should be pinged.
Only issues/PRs carrying the 'waiting-for-author' label are candidates.
"""
author = issue.user.login
# Skip if the trigger label is not present
if not any(label.name == TRIGGER_LABEL for label in issue.labels):
return False
# Skip if author is a team member
if author in team_members:
return False
# Skip if already pinged
if any(label.name == PINGED_LABEL for label in issue.labels):
return False
# Skip if no comments at all
if issue.comments == 0:
return False
# Fetch comments once for both lookups
comments = list(issue.get_comments())
# Find last team member comment
last_team_comment = find_last_team_comment(comments, team_members)
if last_team_comment is None:
return False
# Skip if author replied after the last team comment
if author_replied_after(comments, author, last_team_comment.created_at):
return False
# Check if enough days have passed
days_since = (now - last_team_comment.created_at.astimezone(timezone.utc)).days
if days_since < days_threshold:
return False
return True
def ping(issue: Issue, dry_run: bool) -> bool:
"""Post a reminder comment and add the 'requested-info' label. Returns True on success."""
author = issue.user.login
kind = "PR" if issue.pull_request else "Issue"
if dry_run:
print(f" [DRY RUN] Would ping {kind} #{issue.number} (@{author})")
return True
max_retries = 3
commented = False
labeled = False
for attempt in range(1, max_retries + 1):
try:
if not commented:
issue.create_comment(PING_COMMENT.format(author=author))
commented = True
if not labeled:
issue.add_to_labels(PINGED_LABEL)
labeled = True
print(f" Pinged {kind} #{issue.number} (@{author})")
return True
except Exception as exc:
if attempt < max_retries:
wait = 2 ** attempt # 2s, 4s
print(f" WARN: Attempt {attempt}/{max_retries} failed for {kind} #{issue.number}: {exc}. Retrying in {wait}s...")
time.sleep(wait)
else:
print(f" ERROR: Failed to ping {kind} #{issue.number} after {max_retries} attempts: {exc}")
return False
def main() -> None:
token = os.environ.get("GITHUB_TOKEN")
if not token:
print("ERROR: GITHUB_TOKEN environment variable is required")
sys.exit(1)
repository = os.environ.get("GITHUB_REPOSITORY")
if not repository:
print("ERROR: GITHUB_REPOSITORY environment variable is required")
sys.exit(1)
team_slug = os.environ.get("TEAM_SLUG")
if not team_slug:
print("ERROR: TEAM_SLUG environment variable is required")
sys.exit(1)
days_threshold_raw = os.environ.get("DAYS_THRESHOLD", "4")
try:
days_threshold = int(days_threshold_raw)
except ValueError:
print(f"ERROR: DAYS_THRESHOLD must be a numeric value, got '{days_threshold_raw}'")
sys.exit(1)
dry_run = os.environ.get("DRY_RUN", "false").lower() == "true"
org = repository.split("/")[0]
if dry_run:
print("Running in DRY RUN mode — no comments or labels will be applied.\n")
g = Github(auth=Auth.Token(token))
repo = g.get_repo(repository)
print(f"Fetching team members for {org}/{team_slug}...")
team_members = get_team_members(g, org, team_slug)
print(f"Found {len(team_members)} team members.\n")
now = datetime.now(timezone.utc)
pinged = []
failed = []
scanned = 0
print(f"Scanning open issues and PRs labeled '{TRIGGER_LABEL}' (threshold: {days_threshold} days)...\n")
for issue in repo.get_issues(state="open", labels=[TRIGGER_LABEL]):
scanned += 1
if should_ping(issue, team_members, days_threshold, now):
if ping(issue, dry_run):
pinged.append(issue.number)
else:
failed.append(issue.number)
print(f"\nDone. Scanned {scanned} items, pinged {len(pinged)}, failed {len(failed)}.")
if pinged:
print(f"Pinged: {', '.join(f'#{n}' for n in pinged)}")
if failed:
print(f"Failed: {', '.join(f'#{n}' for n in failed)}")
sys.exit(1)
if __name__ == "__main__":
main()
-297
View File
@@ -1,297 +0,0 @@
# Copyright (c) Microsoft. All rights reserved.
"""Tests for stale_issue_pr_ping.py."""
from __future__ import annotations
import os
import sys
from datetime import datetime, timezone, timedelta
from unittest.mock import MagicMock, patch
import pytest
# Ensure the script directory is importable
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "scripts"))
from stale_issue_pr_ping import (
PINGED_LABEL,
PING_COMMENT,
TRIGGER_LABEL,
author_replied_after,
find_last_team_comment,
get_team_members,
main,
ping,
should_ping,
)
TEAM = {"alice", "bob"}
NOW = datetime(2026, 3, 15, 12, 0, 0, tzinfo=timezone.utc)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _make_comment(login: str | None, created_at: datetime) -> MagicMock:
"""Create a mock IssueComment."""
c = MagicMock()
if login is None:
c.user = None
else:
c.user = MagicMock()
c.user.login = login
c.created_at = created_at
return c
def _make_label(name: str) -> MagicMock:
lbl = MagicMock()
lbl.name = name
return lbl
def _make_issue(
author: str = "external",
labels: list[str] | None = None,
comment_count: int = 1,
comments: list[MagicMock] | None = None,
pull_request: bool = False,
number: int = 42,
) -> MagicMock:
issue = MagicMock()
issue.user = MagicMock()
issue.user.login = author
issue.number = number
# Default to having the trigger label, since the API query pre-filters.
if labels is None:
labels = [TRIGGER_LABEL]
issue.labels = [_make_label(n) for n in labels]
issue.comments = comment_count
issue.pull_request = MagicMock() if pull_request else None
if comments is not None:
issue.get_comments.return_value = comments
return issue
# ---------------------------------------------------------------------------
# find_last_team_comment
# ---------------------------------------------------------------------------
class TestFindLastTeamComment:
def test_returns_last_team_comment(self):
c1 = _make_comment("alice", datetime(2026, 3, 1, tzinfo=timezone.utc))
c2 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
c3 = _make_comment("bob", datetime(2026, 3, 3, tzinfo=timezone.utc))
assert find_last_team_comment([c1, c2, c3], TEAM) is c3
def test_returns_none_when_no_team_comments(self):
c1 = _make_comment("external", datetime(2026, 3, 1, tzinfo=timezone.utc))
assert find_last_team_comment([c1], TEAM) is None
def test_returns_none_for_empty_list(self):
assert find_last_team_comment([], TEAM) is None
def test_skips_deleted_user(self):
c1 = _make_comment(None, datetime(2026, 3, 1, tzinfo=timezone.utc))
c2 = _make_comment("alice", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert find_last_team_comment([c1, c2], TEAM) is c2
def test_only_deleted_users(self):
c1 = _make_comment(None, datetime(2026, 3, 1, tzinfo=timezone.utc))
assert find_last_team_comment([c1], TEAM) is None
# ---------------------------------------------------------------------------
# author_replied_after
# ---------------------------------------------------------------------------
class TestAuthorRepliedAfter:
def test_author_replied(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is True
def test_author_not_replied(self):
after = datetime(2026, 3, 5, tzinfo=timezone.utc)
c1 = _make_comment("external", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
def test_different_user_replied(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment("someone_else", datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
def test_deleted_user_comment(self):
after = datetime(2026, 3, 1, tzinfo=timezone.utc)
c1 = _make_comment(None, datetime(2026, 3, 2, tzinfo=timezone.utc))
assert author_replied_after([c1], "external", after) is False
# ---------------------------------------------------------------------------
# should_ping
# ---------------------------------------------------------------------------
class TestShouldPing:
def test_should_ping_stale_issue(self):
team_comment = _make_comment("alice", NOW - timedelta(days=5))
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is True
def test_skip_team_member_author(self):
issue = _make_issue(author="alice", labels=[TRIGGER_LABEL], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_already_pinged(self):
issue = _make_issue(labels=[TRIGGER_LABEL, PINGED_LABEL], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_no_comments(self):
issue = _make_issue(comment_count=0)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_no_team_comment(self):
c = _make_comment("external", NOW - timedelta(days=5))
issue = _make_issue(comments=[c], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_author_replied(self):
team_c = _make_comment("alice", NOW - timedelta(days=5))
author_c = _make_comment("external", NOW - timedelta(days=3))
issue = _make_issue(comments=[team_c, author_c], comment_count=2)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_skip_not_enough_days(self):
team_comment = _make_comment("alice", NOW - timedelta(days=2))
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is False
def test_aware_datetime_handled(self):
"""Timezone-aware datetimes should not be mangled by astimezone."""
aware_dt = (NOW - timedelta(days=5)).replace(tzinfo=timezone.utc)
team_comment = _make_comment("alice", aware_dt)
issue = _make_issue(comments=[team_comment], comment_count=1)
assert should_ping(issue, TEAM, 4, NOW) is True
def test_naive_datetime_handled(self):
"""Naive datetimes (pre-PyGithub 2.x) should be handled by astimezone."""
naive_dt = (NOW - timedelta(days=5)).replace(tzinfo=None)
team_comment = _make_comment("alice", naive_dt)
issue = _make_issue(comments=[team_comment], comment_count=1)
# astimezone on naive datetime treats it as local time; just verify no crash
should_ping(issue, TEAM, 4, NOW)
# ---------------------------------------------------------------------------
# ping
# ---------------------------------------------------------------------------
class TestPing:
def test_dry_run(self, capsys):
issue = _make_issue()
assert ping(issue, dry_run=True) is True
issue.create_comment.assert_not_called()
assert "DRY RUN" in capsys.readouterr().out
def test_success(self, capsys):
issue = _make_issue()
assert ping(issue, dry_run=False) is True
issue.create_comment.assert_called_once()
issue.add_to_labels.assert_called_once_with(PINGED_LABEL)
@patch("stale_issue_pr_ping.time.sleep")
def test_retry_on_failure(self, mock_sleep):
issue = _make_issue()
issue.create_comment.side_effect = [Exception("net error"), None]
assert ping(issue, dry_run=False) is True
assert issue.create_comment.call_count == 2
mock_sleep.assert_called_once()
@patch("stale_issue_pr_ping.time.sleep")
def test_idempotent_retry_skips_comment_on_label_failure(self, mock_sleep):
"""If create_comment succeeds but add_to_labels fails, retry should not re-comment."""
issue = _make_issue()
issue.add_to_labels.side_effect = [Exception("label error"), None]
assert ping(issue, dry_run=False) is True
# Comment should only be created once even though there were 2 attempts
assert issue.create_comment.call_count == 1
assert issue.add_to_labels.call_count == 2
@patch("stale_issue_pr_ping.time.sleep")
def test_all_retries_fail(self, mock_sleep):
issue = _make_issue()
issue.create_comment.side_effect = Exception("permanent error")
assert ping(issue, dry_run=False) is False
assert issue.create_comment.call_count == 3
# ---------------------------------------------------------------------------
# get_team_members
# ---------------------------------------------------------------------------
class TestGetTeamMembers:
def test_success(self):
g = MagicMock()
member = MagicMock()
member.login = "alice"
g.get_organization.return_value.get_team_by_slug.return_value.get_members.return_value = [member]
assert get_team_members(g, "org", "my-team") == {"alice"}
def test_403_error_message(self, capsys):
from github import GithubException
g = MagicMock()
g.get_organization.return_value.get_team_by_slug.side_effect = GithubException(
403, {"message": "Forbidden"}, None
)
with pytest.raises(SystemExit):
get_team_members(g, "org", "my-team")
out = capsys.readouterr().out
assert "read:org" in out
assert "403" in out
def test_404_error_message(self, capsys):
from github import GithubException
g = MagicMock()
g.get_organization.return_value.get_team_by_slug.side_effect = GithubException(
404, {"message": "Not Found"}, None
)
with pytest.raises(SystemExit):
get_team_members(g, "org", "bad-slug")
out = capsys.readouterr().out
assert "read:org" in out
assert "bad-slug" in out
def test_generic_error(self, capsys):
g = MagicMock()
g.get_organization.side_effect = RuntimeError("boom")
with pytest.raises(SystemExit):
get_team_members(g, "org", "team")
# ---------------------------------------------------------------------------
# main env var validation
# ---------------------------------------------------------------------------
class TestMain:
@patch.dict(os.environ, {
"GITHUB_TOKEN": "tok",
"GITHUB_REPOSITORY": "org/repo",
"TEAM_SLUG": "my-team",
"DAYS_THRESHOLD": "abc",
}, clear=True)
def test_invalid_days_threshold(self, capsys):
with pytest.raises(SystemExit):
main()
assert "numeric" in capsys.readouterr().out
@patch.dict(os.environ, {
"GITHUB_TOKEN": "tok",
"GITHUB_REPOSITORY": "org/repo",
}, clear=True)
def test_missing_team_slug(self, capsys):
with pytest.raises(SystemExit):
main()
assert "TEAM_SLUG" in capsys.readouterr().out
+49 -110
View File
@@ -59,20 +59,20 @@ jobs:
if: steps.filter.outputs.dotnet != 'true'
run: echo "NOT dotnet file"
# Build the full solution (including samples) on all TFMs. No tests.
dotnet-build:
dotnet-build-and-test:
needs: paths-filter
if: needs.paths-filter.outputs.dotnetChanges == 'true'
strategy:
fail-fast: false
matrix:
include:
- { targetFramework: "net10.0", os: "ubuntu-latest", configuration: Release }
- { targetFramework: "net10.0", os: "ubuntu-latest", configuration: Release, integration-tests: true, environment: "integration" }
- { targetFramework: "net9.0", os: "windows-latest", configuration: Debug }
- { targetFramework: "net8.0", os: "ubuntu-latest", configuration: Release }
- { targetFramework: "net472", os: "windows-latest", configuration: Release }
- { targetFramework: "net472", os: "windows-latest", configuration: Release, integration-tests: true, environment: "integration" }
runs-on: ${{ matrix.os }}
environment: ${{ matrix.environment }}
steps:
- uses: actions/checkout@v6
with:
@@ -84,8 +84,18 @@ jobs:
python
workflow-samples
# Start Cosmos DB Emulator for all integration tests and only for unit tests when CosmosDB changes happened)
- name: Start Azure Cosmos DB Emulator
if: ${{ runner.os == 'Windows' && (needs.paths-filter.outputs.cosmosDbChanges == 'true' || (github.event_name != 'pull_request' && matrix.integration-tests)) }}
shell: pwsh
run: |
Write-Host "Launching Azure Cosmos DB Emulator"
Import-Module "$env:ProgramFiles\Azure Cosmos DB Emulator\PSModules\Microsoft.Azure.CosmosDB.Emulator"
Start-CosmosDbEmulator -NoUI -Key "C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
echo "COSMOSDB_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Setup dotnet
uses: actions/setup-dotnet@v5.2.0
uses: actions/setup-dotnet@v5.1.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
- name: Build dotnet solutions
@@ -130,98 +140,25 @@ jobs:
popd
rm -rf "$TEMP_DIR"
# Build src+tests only (no samples) for a single TFM and run tests.
dotnet-test:
needs: paths-filter
if: needs.paths-filter.outputs.dotnetChanges == 'true'
strategy:
fail-fast: false
matrix:
include:
- { targetFramework: "net10.0", os: "ubuntu-latest", configuration: Release, integration-tests: true, environment: "integration" }
- { targetFramework: "net472", os: "windows-latest", configuration: Release, integration-tests: true, environment: "integration" }
runs-on: ${{ matrix.os }}
environment: ${{ matrix.environment }}
steps:
- uses: actions/checkout@v6
with:
persist-credentials: false
sparse-checkout: |
.
.github
dotnet
python
workflow-samples
# Start Cosmos DB Emulator for all integration tests and only for unit tests when CosmosDB changes happened)
- name: Start Azure Cosmos DB Emulator
if: ${{ runner.os == 'Windows' && (needs.paths-filter.outputs.cosmosDbChanges == 'true' || (github.event_name != 'pull_request' && matrix.integration-tests)) }}
shell: pwsh
run: |
Write-Host "Launching Azure Cosmos DB Emulator"
Import-Module "$env:ProgramFiles\Azure Cosmos DB Emulator\PSModules\Microsoft.Azure.CosmosDB.Emulator"
Start-CosmosDbEmulator -NoUI -Key "C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
echo "COSMOSDB_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Setup dotnet
uses: actions/setup-dotnet@v5.2.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
- name: Generate test solution (no samples)
shell: pwsh
run: |
./dotnet/eng/scripts/New-FilteredSolution.ps1 `
-Solution dotnet/agent-framework-dotnet.slnx `
-TargetFramework ${{ matrix.targetFramework }} `
-Configuration ${{ matrix.configuration }} `
-ExcludeSamples `
-OutputPath dotnet/filtered.slnx `
-Verbose
- name: Build src and tests
shell: bash
run: dotnet build dotnet/filtered.slnx -c ${{ matrix.configuration }} -f ${{ matrix.targetFramework }} --warnaserror
- name: Generate test-type filtered solutions
shell: pwsh
run: |
$commonArgs = @{
Solution = "dotnet/filtered.slnx"
TargetFramework = "${{ matrix.targetFramework }}"
Configuration = "${{ matrix.configuration }}"
Verbose = $true
}
./dotnet/eng/scripts/New-FilteredSolution.ps1 @commonArgs `
-TestProjectNameFilter "*UnitTests*" `
-OutputPath dotnet/filtered-unit.slnx
./dotnet/eng/scripts/New-FilteredSolution.ps1 @commonArgs `
-TestProjectNameFilter "*IntegrationTests*" `
-OutputPath dotnet/filtered-integration.slnx
- name: Run Unit Tests
shell: pwsh
working-directory: dotnet
shell: bash
run: |
$coverageSettings = Join-Path $PWD "tests/coverage.runsettings"
$coverageArgs = @()
if ("${{ matrix.targetFramework }}" -eq "${{ env.COVERAGE_FRAMEWORK }}") {
$coverageArgs = @(
"--coverage",
"--coverage-output-format", "cobertura",
"--coverage-settings", $coverageSettings,
"--results-directory", "../TestResults/Coverage/"
)
}
export UT_PROJECTS=$(find ./dotnet -type f -name "*.UnitTests.csproj" | tr '\n' ' ')
for project in $UT_PROJECTS; do
# Query the project's target frameworks using MSBuild with the current configuration
target_frameworks=$(dotnet msbuild $project -getProperty:TargetFrameworks -p:Configuration=${{ matrix.configuration }} -nologo 2>/dev/null | tr -d '\r')
dotnet test --solution ./filtered-unit.slnx `
-f ${{ matrix.targetFramework }} `
-c ${{ matrix.configuration }} `
--no-build -v Normal `
--report-xunit-trx `
--ignore-exit-code 8 `
@coverageArgs
# Check if the project supports the target framework
if [[ "$target_frameworks" == *"${{ matrix.targetFramework }}"* ]]; then
if [[ "${{ matrix.targetFramework }}" == "${{ env.COVERAGE_FRAMEWORK }}" ]]; then
dotnet test -f ${{ matrix.targetFramework }} -c ${{ matrix.configuration }} $project --no-build -v Normal --logger trx --collect:"XPlat Code Coverage" --results-directory:"TestResults/Coverage/" -- DataCollectionRunSettings.DataCollectors.DataCollector.Configuration.ExcludeByAttribute=GeneratedCodeAttribute,CompilerGeneratedAttribute,ExcludeFromCodeCoverageAttribute
else
dotnet test -f ${{ matrix.targetFramework }} -c ${{ matrix.configuration }} $project --no-build -v Normal --logger trx
fi
else
echo "Skipping $project - does not support target framework ${{ matrix.targetFramework }} (supports: $target_frameworks)"
fi
done
env:
# Cosmos DB Emulator connection settings
COSMOSDB_ENDPOINT: https://localhost:8081
@@ -248,19 +185,21 @@ jobs:
id: azure-functions-setup
- name: Run Integration Tests
shell: pwsh
working-directory: dotnet
shell: bash
if: github.event_name != 'pull_request' && matrix.integration-tests
run: |
dotnet test --solution ./filtered-integration.slnx `
-f ${{ matrix.targetFramework }} `
-c ${{ matrix.configuration }} `
--no-build -v Normal `
--report-xunit-trx `
--ignore-exit-code 8 `
--filter-not-trait "Category=IntegrationDisabled" `
--parallel-algorithm aggressive `
--max-threads 2.0x
export INTEGRATION_TEST_PROJECTS=$(find ./dotnet -type f -name "*IntegrationTests.csproj" | tr '\n' ' ')
for project in $INTEGRATION_TEST_PROJECTS; do
# Query the project's target frameworks using MSBuild with the current configuration
target_frameworks=$(dotnet msbuild $project -getProperty:TargetFrameworks -p:Configuration=${{ matrix.configuration }} -nologo 2>/dev/null | tr -d '\r')
# Check if the project supports the target framework
if [[ "$target_frameworks" == *"${{ matrix.targetFramework }}"* ]]; then
dotnet test -f ${{ matrix.targetFramework }} -c ${{ matrix.configuration }} $project --no-build -v Normal --logger trx --filter "Category!=IntegrationDisabled"
else
echo "Skipping $project - does not support target framework ${{ matrix.targetFramework }} (supports: $target_frameworks)"
fi
done
env:
# Cosmos DB Emulator connection settings
COSMOSDB_ENDPOINT: https://localhost:8081
@@ -281,15 +220,15 @@ jobs:
# Generate test reports and check coverage
- name: Generate test reports
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
uses: danielpalme/ReportGenerator-GitHub-Action@5.5.3
uses: danielpalme/ReportGenerator-GitHub-Action@5.5.1
with:
reports: "./TestResults/Coverage/**/*.cobertura.xml"
reports: "./TestResults/Coverage/**/coverage.cobertura.xml"
targetdir: "./TestResults/Reports"
reporttypes: "HtmlInline;JsonSummary"
- name: Upload coverage report artifact
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v6
with:
name: CoverageReport-${{ matrix.os }}-${{ matrix.targetFramework }}-${{ matrix.configuration }} # Artifact name
path: ./TestResults/Reports # Directory containing files to upload
@@ -297,13 +236,13 @@ jobs:
- name: Check coverage
if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
shell: pwsh
run: ./dotnet/eng/scripts/dotnet-check-coverage.ps1 -JsonReportPath "TestResults/Reports/Summary.json" -CoverageThreshold $env:COVERAGE_THRESHOLD
run: .github/workflows/dotnet-check-coverage.ps1 -JsonReportPath "TestResults/Reports/Summary.json" -CoverageThreshold $env:COVERAGE_THRESHOLD
# This final job is required to satisfy the merge queue. It must only run (or succeed) if no tests failed
dotnet-build-and-test-check:
if: always()
runs-on: ubuntu-latest
needs: [dotnet-build, dotnet-test]
needs: [dotnet-build-and-test]
steps:
- name: Get Date
shell: bash
+2 -1
View File
@@ -86,10 +86,11 @@ jobs:
run: docker pull mcr.microsoft.com/dotnet/sdk:${{ matrix.dotnet }}
# This step will run dotnet format on each of the unique csproj files and fail if any changes are made
# exclude-diagnostics should be removed after fixes for IL2026 and IL3050 are out: https://github.com/dotnet/sdk/issues/51136
- name: Run dotnet format
if: steps.find-csproj.outputs.csproj_files != ''
run: |
for csproj in ${{ steps.find-csproj.outputs.csproj_files }}; do
echo "Running dotnet format on $csproj"
docker run --rm -v $(pwd):/app -w /app mcr.microsoft.com/dotnet/sdk:${{ matrix.dotnet }} /bin/sh -c "dotnet format $csproj --verify-no-changes --verbosity diagnostic"
docker run --rm -v $(pwd):/app -w /app mcr.microsoft.com/dotnet/sdk:${{ matrix.dotnet }} /bin/sh -c "dotnet format $csproj --verify-no-changes --verbosity diagnostic --exclude-diagnostics IL2026 IL3050"
done
@@ -50,7 +50,7 @@ jobs:
echo "COSMOS_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
- name: Setup dotnet
uses: actions/setup-dotnet@v5.2.0
uses: actions/setup-dotnet@v5.1.0
with:
global-json-file: ${{ github.workspace }}/dotnet/global.json
+1 -4
View File
@@ -29,7 +29,4 @@ jobs:
token: ${{ secrets.GITHUB_TOKEN }}
timeout: 3600
interval: 30
# "Cleanup artifacts", "Agent", "Prepare", and "Upload results" are check runs
# created by an org-level GitHub App (MSDO), not by any workflow in this repo.
# They are outside our control and their transient failures should not block merges.
ignored: CodeQL,CodeQL analysis (csharp),Cleanup artifacts,Agent,Prepare,Upload results
ignored: CodeQL,CodeQL analysis (csharp)
+2 -1
View File
@@ -41,7 +41,8 @@ ENFORCED_TARGETS: set[str] = {
"packages.purview.agent_framework_purview",
"packages.anthropic.agent_framework_anthropic",
"packages.azure-ai-search.agent_framework_azure_ai_search",
"packages.openai.agent_framework_openai",
"packages.core.agent_framework.azure",
"packages.core.agent_framework.openai",
# Individual files (if you want to enforce specific files instead of whole packages)
"packages/core/agent_framework/observability.py",
# Add more targets here as coverage improves
+10 -8
View File
@@ -18,7 +18,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.11"]
python-version: ["3.10"]
runs-on: ubuntu-latest
continue-on-error: true
defaults:
@@ -55,7 +55,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.11"]
python-version: ["3.10"]
runs-on: ubuntu-latest
continue-on-error: true
defaults:
@@ -75,7 +75,7 @@ jobs:
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run syntax and pyright across packages
- name: Run fmt, lint, pyright in parallel across packages
run: uv run poe check-packages
samples-markdown:
@@ -84,7 +84,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.11"]
python-version: ["3.10"]
runs-on: ubuntu-latest
continue-on-error: true
defaults:
@@ -104,8 +104,10 @@ jobs:
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run samples checks
run: uv run poe check -S
- name: Run samples lint
run: uv run poe samples-lint
- name: Run samples syntax check
run: uv run poe samples-syntax
- name: Run markdown code lint
run: uv run poe markdown-code-lint
@@ -115,7 +117,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python-version: ["3.11"]
python-version: ["3.10"]
runs-on: ubuntu-latest
continue-on-error: true
defaults:
@@ -138,4 +140,4 @@ jobs:
- name: Run Mypy
env:
GITHUB_BASE_REF: ${{ github.event.pull_request.base.ref || github.base_ref || 'main' }}
run: uv run python scripts/workspace_poe_tasks.py ci-mypy
run: uv run poe ci-mypy
@@ -1,216 +0,0 @@
# Probe the highest allowed dependency versions, then open issues/PRs from the passing updates.
name: Python - Dependency Range Validation
on:
workflow_dispatch:
permissions:
contents: write
issues: write
pull-requests: write
env:
UV_CACHE_DIR: /tmp/.uv-cache
jobs:
dependency-range-validation:
name: Dependency Range Validation
runs-on: ubuntu-latest
env:
# For now only run 3.13, if we do encounter situations where there are mismatches between packages and python versions (other then 3.10 and 3.14 which are known to not be able to install everything)
# then we will have to reevaluate.
UV_PYTHON: "3.13"
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up python and install the project
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run dependency range validation
id: validate_ranges
# Keep workflow running so we can still publish diagnostics from this run.
continue-on-error: true
run: uv run poe validate-dependency-bounds-project --mode upper --package "*"
working-directory: ./python
- name: Upload dependency range report
# Always publish the report so failures are inspectable even when validation fails.
if: always()
uses: actions/upload-artifact@v7
with:
name: dependency-range-results
path: python/scripts/dependencies/dependency-range-results.json
if-no-files-found: warn
- name: Create issues for failed dependency candidates
# Always process the report so failed candidates create actionable tracking issues.
if: always()
uses: actions/github-script@v8
with:
script: |
const fs = require("fs")
const reportPath = "python/scripts/dependencies/dependency-range-results.json"
if (!fs.existsSync(reportPath)) {
core.warning(`No dependency range report found at ${reportPath}`)
return
}
const report = JSON.parse(fs.readFileSync(reportPath, "utf8"))
const dependencyFailures = []
for (const packageResult of report.packages ?? []) {
for (const dependency of packageResult.dependencies ?? []) {
const candidateVersions = new Set(dependency.candidate_versions ?? [])
const failedAttempts = (dependency.attempts ?? []).filter(
(attempt) => attempt.status === "failed" && candidateVersions.has(attempt.trial_upper)
)
if (!failedAttempts.length) {
continue
}
const failuresByVersion = new Map()
for (const attempt of failedAttempts) {
const version = attempt.trial_upper || "unknown"
if (!failuresByVersion.has(version)) {
failuresByVersion.set(version, attempt.error || "No error output captured.")
}
}
dependencyFailures.push({
packageName: packageResult.package_name,
projectPath: packageResult.project_path,
dependencyName: dependency.name,
originalRequirements: dependency.original_requirements ?? [],
finalRequirements: dependency.final_requirements ?? [],
failedVersions: [...failuresByVersion.entries()].map(([version, error]) => ({ version, error })),
})
}
}
if (!dependencyFailures.length) {
core.info("No failing dependency candidates found.")
return
}
const owner = context.repo.owner
const repo = context.repo.repo
const openIssues = await github.paginate(github.rest.issues.listForRepo, {
owner,
repo,
state: "open",
per_page: 100,
})
const openIssueTitles = new Set(
openIssues.filter((issue) => !issue.pull_request).map((issue) => issue.title)
)
const formatError = (message) => String(message || "No error output captured.").replace(/```/g, "'''")
for (const failure of dependencyFailures) {
const title = `Dependency validation failed: ${failure.dependencyName} (${failure.packageName})`
if (openIssueTitles.has(title)) {
core.info(`Issue already exists: ${title}`)
continue
}
const visibleFailures = failure.failedVersions.slice(0, 5)
const omittedCount = failure.failedVersions.length - visibleFailures.length
const failureDetails = visibleFailures
.map(
(entry) =>
`- \`${entry.version}\`\n\n\`\`\`\n${formatError(entry.error).slice(0, 3500)}\n\`\`\``
)
.join("\n\n")
const body = [
"Automated dependency range validation found candidate versions that failed checks.",
"",
`- Package: \`${failure.packageName}\``,
`- Project path: \`${failure.projectPath}\``,
`- Dependency: \`${failure.dependencyName}\``,
`- Original requirements: ${
failure.originalRequirements.length
? failure.originalRequirements.map((value) => `\`${value}\``).join(", ")
: "_none_"
}`,
`- Final requirements after run: ${
failure.finalRequirements.length
? failure.finalRequirements.map((value) => `\`${value}\``).join(", ")
: "_none_"
}`,
"",
"### Failed versions and errors",
failureDetails,
omittedCount > 0 ? `\n_Additional failed versions omitted: ${omittedCount}_` : "",
"",
`Workflow run: ${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`,
].join("\n")
await github.rest.issues.create({
owner,
repo,
title,
body,
})
openIssueTitles.add(title)
core.info(`Created issue: ${title}`)
}
- name: Refresh lockfile
# Only refresh lockfile after a clean validation to avoid committing known-bad ranges.
if: steps.validate_ranges.outcome == 'success'
run: uv lock --upgrade
working-directory: ./python
- name: Commit and push dependency updates
id: commit_updates
if: steps.validate_ranges.outcome == 'success'
run: |
BRANCH="automation/python-dependency-range-updates"
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git checkout -B "${BRANCH}"
git add python/packages/*/pyproject.toml python/uv.lock
if git diff --cached --quiet; then
echo "has_changes=false" >> "$GITHUB_OUTPUT"
echo "No dependency updates to commit."
exit 0
fi
git commit -m "chore: update dependency ranges"
git push --force-with-lease --set-upstream origin "${BRANCH}"
echo "has_changes=true" >> "$GITHUB_OUTPUT"
- name: Create or update pull request with GitHub CLI
# Only open/update PRs for validated updates to keep automation branches trustworthy.
if: steps.validate_ranges.outcome == 'success' && steps.commit_updates.outputs.has_changes == 'true'
run: |
BRANCH="automation/python-dependency-range-updates"
PR_TITLE="Python: chore: update dependency ranges"
PR_BODY_FILE="$(mktemp)"
cat > "${PR_BODY_FILE}" <<'EOF'
This PR was generated by the dependency range validation workflow.
- Ran `uv run poe validate-dependency-bounds-project --mode upper --package "*"`
- Updated package dependency bounds
- Refreshed `python/uv.lock` with `uv lock --upgrade`
EOF
PR_NUMBER="$(gh pr list --head "${BRANCH}" --base main --state open --json number --jq '.[0].number')"
if [ -n "${PR_NUMBER}" ]; then
gh pr edit "${PR_NUMBER}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
else
gh pr create --base main --head "${BRANCH}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
fi
@@ -1,91 +0,0 @@
name: Python - Dev Dependency Upgrade
on:
workflow_dispatch:
permissions:
contents: write
pull-requests: write
env:
UV_CACHE_DIR: /tmp/.uv-cache
jobs:
upgrade-dev-dependencies:
name: Upgrade Dev Dependencies
runs-on: ubuntu-latest
env:
UV_PYTHON: "3.13"
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Set up python and install the project
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
env:
UV_CACHE_DIR: /tmp/.uv-cache
- name: Upgrade dev dependencies and validate workspace
run: uv run poe upgrade-dev-dependencies
working-directory: ./python
- name: Commit and push dev dependency updates
id: commit_updates
run: |
BRANCH="automation/python-dev-dependency-updates"
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git checkout -B "${BRANCH}"
git add python/pyproject.toml python/packages/*/pyproject.toml python/uv.lock
if git diff --cached --quiet; then
echo "has_changes=false" >> "$GITHUB_OUTPUT"
echo "No dev dependency updates to commit."
exit 0
fi
git commit -F- <<'EOF'
Python: chore: upgrade dev dependencies
EOF
git push --force-with-lease --set-upstream origin "${BRANCH}"
echo "has_changes=true" >> "$GITHUB_OUTPUT"
- name: Create or update pull request with GitHub CLI
if: steps.commit_updates.outputs.has_changes == 'true'
run: |
BRANCH="automation/python-dev-dependency-updates"
PR_TITLE="Python: chore: upgrade dev dependencies"
PR_BODY_FILE="$(mktemp)"
cat > "${PR_BODY_FILE}" <<'EOF'
### Motivation and Context
This automated update refreshes Python dev dependency pins across the workspace and reruns the repo validation gates before opening a pull request.
### Description
- Ran `uv run poe upgrade-dev-dependencies`
- Refreshed dev dependency pins in workspace `pyproject.toml` files
- Refreshed `python/uv.lock` with `uv lock --upgrade`
- Reinstalled from the frozen lockfile and reran `check`, `typing`, and `test`
### Contribution Checklist
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [Contribution Guidelines](https://github.com/microsoft/agent-framework/blob/main/CONTRIBUTING.md)
- [x] All unit tests pass, and I have added new tests where possible
- [ ] **Is this a breaking change?** If yes, add "[BREAKING]" prefix to the title of the PR.
EOF
PR_NUMBER="$(gh pr list --head "${BRANCH}" --base main --state open --json number --jq '.[0].number')"
if [ -n "${PR_NUMBER}" ]; then
gh pr edit "${PR_NUMBER}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
else
gh pr create --base main --head "${BRANCH}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
fi
+20 -68
View File
@@ -48,8 +48,9 @@ jobs:
os: ${{ runner.os }}
- name: Test with pytest (unit tests only)
run: >
uv run poe test -A
uv run poe all-tests
-m "not integration"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -60,10 +61,9 @@ jobs:
environment: integration
timeout-minutes: 60
env:
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
defaults:
run:
@@ -82,8 +82,8 @@ jobs:
- name: Test with pytest (OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests
-m "integration and not azure"
packages/core/tests/openai
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -97,8 +97,7 @@ jobs:
env:
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
defaults:
run:
@@ -123,11 +122,7 @@ jobs:
- name: Test with pytest (Azure OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
packages/openai/tests/openai/test_openai_chat_client_azure.py
packages/openai/tests/openai/test_openai_embedding_client_azure.py
packages/azure-ai/tests/azure_openai
--ignore=packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/core/tests/azure
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
@@ -157,13 +152,6 @@ jobs:
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Start local MCP server
id: local-mcp
uses: ./.github/actions/setup-local-mcp-server
with:
fallback_url: ${{ env.LOCAL_MCP_URL }}
- name: Prefer local MCP URL when available
run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
- name: Test with pytest (Anthropic, Ollama, MCP integration)
run: >
uv run pytest --import-mode=importlib
@@ -174,26 +162,6 @@ jobs:
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
- name: Stop local MCP server
if: always()
shell: bash
run: |
set -euo pipefail
server_pid="${{ steps.local-mcp.outputs.pid }}"
if [[ -z "$server_pid" ]]; then
exit 0
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
for _ in $(seq 1 10); do
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
sleep 1
done
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
# Azure Functions + Durable Task integration tests
python-tests-functions:
@@ -202,17 +170,13 @@ jobs:
environment: integration
timeout-minutes: 60
env:
UV_PYTHON: "3.11"
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
UV_PYTHON: "3.10"
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
FUNCTIONS_WORKER_RUNTIME: "python"
DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -246,23 +210,18 @@ jobs:
packages/durabletask/tests/integration_tests
-m integration
-n logical --dist worksteal
-x
--timeout=360 --session-timeout=900 --timeout_method thread
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
# Foundry integration tests
python-tests-foundry:
name: Python Integration Tests - Foundry
# Azure AI integration tests
python-tests-azure-ai:
name: Python Integration Tests - Azure AI
runs-on: ubuntu-latest
environment: integration
timeout-minutes: 60
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
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 }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
defaults:
run:
@@ -286,14 +245,7 @@ jobs:
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest
timeout-minutes: 15
run: >
uv run pytest --import-mode=importlib
packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/foundry/tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
# Azure Cosmos integration tests
python-tests-cosmos:
@@ -350,7 +302,7 @@ jobs:
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-foundry,
python-tests-azure-ai,
python-tests-cosmos
]
steps:
-4
View File
@@ -67,7 +67,6 @@ jobs:
with:
python-version: ${{ matrix.python-version }}
os: ${{ runner.os }}
exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
env:
# Configure a constant location for the uv cache
UV_CACHE_DIR: /tmp/.uv-cache
@@ -76,9 +75,6 @@ jobs:
- name: Run lab tests
run: cd packages/lab && uv run poe test
- name: Run resource-intensive lab tests
run: cd packages/lab && uv run pytest -m "resource_intensive and not integration" --junitxml=test-results-resource-intensive.xml
- name: Run lab lint
run: cd packages/lab && uv run poe lint
+21 -82
View File
@@ -47,9 +47,6 @@ jobs:
filters: |
python:
- 'python/**'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
core:
- 'python/packages/core/agent_framework/_*.py'
- 'python/packages/core/agent_framework/_workflows/**'
@@ -57,30 +54,20 @@ jobs:
- 'python/packages/core/agent_framework/observability.py'
openai:
- 'python/packages/core/agent_framework/openai/**'
- 'python/packages/openai/**'
- 'python/samples/**/providers/openai/**'
- 'python/packages/core/tests/openai/**'
azure:
- 'python/packages/openai/**'
- 'python/packages/core/agent_framework/azure/**'
- 'python/packages/azure-ai/agent_framework_azure_ai/_deprecated_azure_openai.py'
- 'python/packages/azure-ai/tests/azure_openai/**'
- 'python/samples/**/providers/azure/openai_chat_completion_client_azure*.py'
- 'python/packages/core/tests/azure/**'
misc:
- 'python/packages/anthropic/**'
- 'python/packages/ollama/**'
- 'python/packages/core/agent_framework/_mcp.py'
- 'python/packages/core/tests/core/test_mcp.py'
- 'python/scripts/local_mcp_streamable_http_server.py'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
functions:
- 'python/packages/azurefunctions/**'
- 'python/packages/durabletask/**'
azure-ai:
- 'python/packages/azure-ai/**'
- 'python/packages/foundry/**'
- 'python/samples/**/providers/foundry/**'
cosmos:
- 'python/packages/azure-cosmos/**'
# run only if 'python' files were changed
@@ -113,8 +100,9 @@ jobs:
os: ${{ runner.os }}
- name: Test with pytest (unit tests only)
run: >
uv run poe test -A
uv run poe all-tests
-m "not integration"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
@@ -141,10 +129,9 @@ jobs:
runs-on: ubuntu-latest
environment: integration
env:
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
defaults:
run:
@@ -160,8 +147,8 @@ jobs:
- name: Test with pytest (OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests
-m "integration and not azure"
packages/core/tests/openai
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
@@ -196,8 +183,7 @@ jobs:
env:
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
defaults:
run:
@@ -220,11 +206,7 @@ jobs:
- name: Test with pytest (Azure OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
packages/openai/tests/openai/test_openai_chat_client_azure.py
packages/openai/tests/openai/test_openai_embedding_client_azure.py
packages/azure-ai/tests/azure_openai
--ignore=packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/core/tests/azure
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
@@ -272,13 +254,6 @@ jobs:
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Start local MCP server
id: local-mcp
uses: ./.github/actions/setup-local-mcp-server
with:
fallback_url: ${{ env.LOCAL_MCP_URL }}
- name: Prefer local MCP URL when available
run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
- name: Test with pytest (Anthropic, Ollama, MCP integration)
run: >
uv run pytest --import-mode=importlib
@@ -290,26 +265,6 @@ jobs:
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
- name: Stop local MCP server
if: always()
shell: bash
run: |
set -euo pipefail
server_pid="${{ steps.local-mcp.outputs.pid }}"
if [[ -z "$server_pid" ]]; then
exit 0
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
for _ in $(seq 1 10); do
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
sleep 1
done
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
@@ -333,17 +288,13 @@ jobs:
runs-on: ubuntu-latest
environment: integration
env:
UV_PYTHON: "3.11"
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
UV_PYTHON: "3.10"
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
FUNCTIONS_WORKER_RUNTIME: "python"
DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -375,8 +326,7 @@ jobs:
packages/durabletask/tests/integration_tests
-m integration
-n logical --dist worksteal
-x
--timeout=360 --session-timeout=900 --timeout_method thread
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
working-directory: ./python
- name: Surface failing tests
@@ -389,8 +339,8 @@ jobs:
fail-on-empty: false
title: Functions integration test results
python-tests-foundry:
name: Python Integration Tests - Foundry
python-tests-azure-ai:
name: Python Tests - Azure AI
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
@@ -403,10 +353,6 @@ jobs:
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
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 }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
defaults:
run:
@@ -428,14 +374,7 @@ jobs:
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest
timeout-minutes: 15
run: >
uv run pytest --import-mode=importlib
packages/azure-ai/tests/azure_openai/test_azure_responses_client_foundry.py
packages/foundry/tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
working-directory: ./python
- name: Test Azure AI samples
timeout-minutes: 10
@@ -522,7 +461,7 @@ jobs:
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-foundry,
python-tests-azure-ai,
python-tests-cosmos,
]
steps:
+17 -467
View File
@@ -41,23 +41,16 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 01-get-started --save-report --report-name 01-get-started
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-01-get-started
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-02-agents:
name: Validate 02-agents
@@ -67,20 +60,14 @@ jobs:
# Azure AI configuration
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
# Azure OpenAI configuration
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
# OpenAI configuration
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
# GitHub MCP
GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
# Observability
ENABLE_INSTRUMENTATION: "true"
defaults:
@@ -97,351 +84,16 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "FOUNDRY_PROJECT_ENDPOINT=$FOUNDRY_PROJECT_ENDPOINT" >> .env
echo "FOUNDRY_MODEL=$FOUNDRY_MODEL" >> .env
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=$AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
echo "GITHUB_PAT=$GITHUB_PAT" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents --exclude providers --save-report --report-name 02-agents
cd scripts && uv run python -m sample_validation --subdir 02-agents --save-report --report-name 02-agents
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-02-agents
path: python/samples/sample_validation/reports/
validate-02-agents-openai:
name: Validate 02-agents/providers/openai
runs-on: ubuntu-latest
environment: integration
env:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_MODEL=$OPENAI_MODEL" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/openai --save-report --report-name 02-agents-openai
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-openai
path: python/samples/sample_validation/reports/
validate-02-agents-azure:
name: Validate 02-agents/providers/azure
runs-on: ubuntu-latest
environment: integration
env:
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/azure --save-report --report-name 02-agents-azure
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-azure
path: python/samples/sample_validation/reports/
validate-02-agents-anthropic:
name: Validate 02-agents/providers/anthropic
runs-on: ubuntu-latest
environment: integration
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
ANTHROPIC_CHAT_MODEL_ID: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY" >> .env
echo "ANTHROPIC_CHAT_MODEL_ID=$ANTHROPIC_CHAT_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/anthropic --save-report --report-name 02-agents-anthropic
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-anthropic
path: python/samples/sample_validation/reports/
validate-02-agents-github-copilot:
name: Validate 02-agents/providers/github_copilot
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/github_copilot --save-report --report-name 02-agents-github-copilot
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-github-copilot
path: python/samples/sample_validation/reports/
validate-02-agents-amazon:
name: Validate 02-agents/providers/amazon
if: false # Temporarily disabled - requires AWS credentials
runs-on: ubuntu-latest
environment: integration
env:
BEDROCK_CHAT_MODEL_ID: ${{ vars.BEDROCK__CHATMODELID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/amazon --save-report --report-name 02-agents-amazon
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-amazon
path: python/samples/sample_validation/reports/
validate-02-agents-ollama:
name: Validate 02-agents/providers/ollama
if: false # Temporarily disabled - requires local Ollama server
runs-on: ubuntu-latest
environment: integration
env:
OLLAMA_MODEL: ${{ vars.OLLAMA__MODEL }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/ollama --save-report --report-name 02-agents-ollama
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-ollama
path: python/samples/sample_validation/reports/
validate-02-agents-foundry:
name: Validate 02-agents/providers/foundry
runs-on: ubuntu-latest
environment: integration
env:
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "FOUNDRY_PROJECT_ENDPOINT=$FOUNDRY_PROJECT_ENDPOINT" >> .env
echo "FOUNDRY_MODEL=$FOUNDRY_MODEL" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/foundry --save-report --report-name 02-agents-foundry
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-foundry
path: python/samples/sample_validation/reports/
validate-02-agents-copilotstudio:
name: Validate 02-agents/providers/copilotstudio
if: false # Temporarily disabled - requires Copilot Studio setup
runs-on: ubuntu-latest
environment: integration
env:
COPILOTSTUDIOAGENT__ENVIRONMENTID: ${{ secrets.COPILOTSTUDIOAGENT__ENVIRONMENTID }}
COPILOTSTUDIOAGENT__SCHEMANAME: ${{ secrets.COPILOTSTUDIOAGENT__SCHEMANAME }}
COPILOTSTUDIOAGENT__TENANTID: ${{ secrets.COPILOTSTUDIOAGENT__TENANTID }}
COPILOTSTUDIOAGENT__AGENTAPPID: ${{ secrets.COPILOTSTUDIOAGENT__AGENTAPPID }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "COPILOTSTUDIOAGENT__ENVIRONMENTID=$COPILOTSTUDIOAGENT__ENVIRONMENTID" >> .env
echo "COPILOTSTUDIOAGENT__SCHEMANAME=$COPILOTSTUDIOAGENT__SCHEMANAME" >> .env
echo "COPILOTSTUDIOAGENT__TENANTID=$COPILOTSTUDIOAGENT__TENANTID" >> .env
echo "COPILOTSTUDIOAGENT__AGENTAPPID=$COPILOTSTUDIOAGENT__AGENTAPPID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/copilotstudio --save-report --report-name 02-agents-copilotstudio
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-copilotstudio
path: python/samples/sample_validation/reports/
validate-02-agents-custom:
name: Validate 02-agents/providers/custom
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Setup environment
uses: ./.github/actions/sample-validation-setup
with:
azure-client-id: ${{ secrets.AZURE_CLIENT_ID }}
azure-tenant-id: ${{ secrets.AZURE_TENANT_ID }}
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/custom --save-report --report-name 02-agents-custom
- name: Upload validation report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-report-02-agents-custom
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-03-workflows:
name: Validate 03-workflows
@@ -449,8 +101,6 @@ jobs:
environment: integration
env:
# Azure AI configuration
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
# Azure OpenAI configuration
@@ -471,30 +121,20 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "FOUNDRY_PROJECT_ENDPOINT=$FOUNDRY_PROJECT_ENDPOINT" >> .env
echo "FOUNDRY_MODEL=$FOUNDRY_MODEL" >> .env
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir 03-workflows --save-report --report-name 03-workflows
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-03-workflows
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-04-hosting:
name: Validate 04-hosting
if: false # Temporarily disabled because of sample complexity
if: false # Temporarily disabled because of sample complexity
runs-on: ubuntu-latest
environment: integration
env:
@@ -525,15 +165,15 @@ jobs:
cd scripts && uv run python -m sample_validation --subdir 04-hosting --save-report --report-name 04-hosting
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-04-hosting
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-05-end-to-end:
name: Validate 05-end-to-end
if: false # Temporarily disabled because of sample complexity
if: false # Temporarily disabled because of sample complexity
runs-on: ubuntu-latest
environment: integration
env:
@@ -569,11 +209,11 @@ jobs:
cd scripts && uv run python -m sample_validation --subdir 05-end-to-end --save-report --report-name 05-end-to-end
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-05-end-to-end
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-autogen-migration:
name: Validate autogen-migration
@@ -590,7 +230,6 @@ jobs:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
defaults:
run:
working-directory: python
@@ -605,26 +244,16 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir autogen-migration --save-report --report-name autogen-migration
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-autogen-migration
path: python/samples/sample_validation/reports/
path: python/scripts/sample_validation/reports/
validate-semantic-kernel-migration:
name: Validate semantic-kernel-migration
@@ -642,7 +271,6 @@ jobs:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
# Copilot Studio
COPILOTSTUDIOAGENT__ENVIRONMENTID: ${{ secrets.COPILOTSTUDIOAGENT__ENVIRONMENTID }}
COPILOTSTUDIOAGENT__SCHEMANAME: ${{ secrets.COPILOTSTUDIOAGENT__SCHEMANAME }}
@@ -662,91 +290,13 @@ jobs:
azure-subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
os: ${{ runner.os }}
- name: Create .env for samples
run: |
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
echo "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=$AZURE_OPENAI_CHAT_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=$AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME" >> .env
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
echo "COPILOTSTUDIOAGENT__ENVIRONMENTID=$COPILOTSTUDIOAGENT__ENVIRONMENTID" >> .env
echo "COPILOTSTUDIOAGENT__SCHEMANAME=$COPILOTSTUDIOAGENT__SCHEMANAME" >> .env
echo "COPILOTSTUDIOAGENT__TENANTID=$COPILOTSTUDIOAGENT__TENANTID" >> .env
echo "COPILOTSTUDIOAGENT__AGENTAPPID=$COPILOTSTUDIOAGENT__AGENTAPPID" >> .env
- name: Run sample validation
run: |
cd scripts && uv run python -m sample_validation --subdir semantic-kernel-migration --save-report --report-name semantic-kernel-migration
- name: Upload validation report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
if: always()
with:
name: validation-report-semantic-kernel-migration
path: python/samples/sample_validation/reports/
aggregate-results:
name: Aggregate Results
runs-on: ubuntu-latest
if: always()
needs:
- validate-01-get-started
- validate-02-agents
- validate-02-agents-openai
- validate-02-agents-azure
- validate-02-agents-anthropic
- validate-02-agents-github-copilot
- validate-02-agents-amazon
- validate-02-agents-ollama
- validate-02-agents-foundry
- validate-02-agents-copilotstudio
- validate-02-agents-custom
- validate-03-workflows
- validate-04-hosting
- validate-05-end-to-end
- validate-autogen-migration
- validate-semantic-kernel-migration
steps:
- uses: actions/checkout@v6
- name: Download all validation reports
uses: actions/download-artifact@v7
with:
pattern: validation-report-*
path: reports/
merge-multiple: true
- name: Restore validation history
id: cache-restore
uses: actions/cache/restore@v4
with:
path: validation-history/
key: validation-history-${{ github.run_id }}
restore-keys: |
validation-history-
- name: Aggregate results and generate trend report
run: |
python3 python/scripts/sample_validation/aggregate.py \
reports/ \
validation-history/history.json \
trend-report.md
- name: Write trend report to job summary
run: cat trend-report.md >> "$GITHUB_STEP_SUMMARY"
- name: Save validation history
uses: actions/cache/save@v4
with:
path: validation-history/
key: validation-history-${{ github.run_id }}
- name: Upload trend report
uses: actions/upload-artifact@v7
if: always()
with:
name: validation-trend-report
path: trend-report.md
path: python/scripts/sample_validation/reports/
@@ -21,7 +21,7 @@ jobs:
steps:
- uses: actions/checkout@v6
- name: Download coverage report
uses: actions/download-artifact@v8
uses: actions/download-artifact@v7
with:
github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
run-id: ${{ github.event.workflow_run.id }}
@@ -46,7 +46,7 @@ jobs:
echo "PR_NUMBER=$PR_NUMBER" >> "$GITHUB_ENV"
- name: Pytest coverage comment
id: coverageComment
uses: MishaKav/pytest-coverage-comment@v1.6.0
uses: MishaKav/pytest-coverage-comment@v1.2.0
with:
github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
issue-number: ${{ env.PR_NUMBER }}
+4 -4
View File
@@ -20,7 +20,7 @@ jobs:
run:
working-directory: python
env:
UV_PYTHON: "3.11"
UV_PYTHON: "3.10"
steps:
- uses: actions/checkout@v6
# Save the PR number to a file since the workflow_run event
@@ -32,17 +32,17 @@ jobs:
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
python-version: ${{ matrix.python-version }}
os: ${{ runner.os }}
env:
# Configure a constant location for the uv cache
UV_CACHE_DIR: /tmp/.uv-cache
- name: Run all tests with coverage report
run: uv run poe test -A -C --cov-report=xml:python-coverage.xml -q --junitxml=pytest.xml
run: uv run poe all-tests-cov --cov-report=xml:python-coverage.xml -q --junitxml=pytest.xml
- name: Check coverage threshold
run: python ${{ github.workspace }}/.github/workflows/python-check-coverage.py python-coverage.xml ${{ env.COVERAGE_THRESHOLD }}
- name: Upload coverage report
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v6
with:
path: |
python/python-coverage.xml
+1 -2
View File
@@ -34,13 +34,12 @@ jobs:
with:
python-version: ${{ matrix.python-version }}
os: ${{ runner.os }}
exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
env:
# Configure a constant location for the uv cache
UV_CACHE_DIR: /tmp/.uv-cache
# Unit tests
- name: Run all tests
run: uv run poe test -A
run: uv run poe all-tests
working-directory: ./python
# Surface failing tests
-49
View File
@@ -1,49 +0,0 @@
name: Stale issue and PR ping
on:
schedule:
- cron: '0 0 * * *' # Midnight UTC daily
workflow_dispatch:
inputs:
days_threshold:
description: 'Days of silence before pinging the author'
required: false
default: '4'
dry_run:
description: 'Log what would be pinged without taking action'
required: false
default: 'false'
type: choice
options:
- 'false'
- 'true'
concurrency:
group: stale-issue-pr-ping
cancel-in-progress: true
jobs:
ping_stale:
name: "Ping stale issues and PRs"
runs-on: ubuntu-latest
permissions:
contents: read
issues: write
pull-requests: write
steps:
- uses: actions/checkout@v6
- uses: actions/setup-python@v5
with:
python-version: '3.13'
- name: Install dependencies
run: pip install PyGithub==2.6.0
- name: Run stale issue/PR ping
run: python .github/scripts/stale_issue_pr_ping.py
env:
GITHUB_TOKEN: ${{ secrets.GH_ACTIONS_PR_WRITE }}
TEAM_SLUG: ${{ secrets.DEVELOPER_TEAM }}
DAYS_THRESHOLD: ${{ github.event.inputs.days_threshold || '4' }}
DRY_RUN: ${{ github.event.inputs.dry_run || 'false' }}
-3
View File
@@ -205,9 +205,6 @@ WARP.md
**/memory-bank/
**/projectBrief.md
**/tmpclaude*
# Dependency-bound validation reports
python/scripts/dependency-*-results.json
python/scripts/dependencies/dependency-*-results.json
# Azurite storage emulator files
*/__azurite_db_blob__.json*
+5 -5
View File
@@ -4,8 +4,8 @@ status: accepted
contact: westey-m
date: 2025-07-10 {YYYY-MM-DD when the decision was last updated}
deciders: sergeymenshykh, markwallace, rbarreto, dmytrostruk, westey-m, eavanvalkenburg, stephentoub
consulted:
informed:
consulted:
informed:
---
# Agent Run Responses Design
@@ -64,7 +64,7 @@ Approaches observed from the compared SDKs:
| AutoGen | **Approach 1** Separates messages into Agent-Agent (maps to Primary) and Internal (maps to Secondary) and these are returned as separate properties on the agent response object. See [types of messages](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/messages.html#types-of-messages) and [Response](https://microsoft.github.io/autogen/stable/reference/python/autogen_agentchat.base.html#autogen_agentchat.base.Response) | **Approach 2** Returns a stream of internal events and the last item is a Response object. See [ChatAgent.on_messages_stream](https://microsoft.github.io/autogen/stable/reference/python/autogen_agentchat.base.html#autogen_agentchat.base.ChatAgent.on_messages_stream) |
| OpenAI Agent SDK | **Approach 1** Separates new_items (Primary+Secondary) from final output (Primary) as separate properties on the [RunResult](https://github.com/openai/openai-agents-python/blob/main/src/agents/result.py#L39) | **Approach 1** Similar to non-streaming, has a way of streaming updates via a method on the response object which includes all data, and then a separate final output property on the response object which is populated only when the run is complete. See [RunResultStreaming](https://github.com/openai/openai-agents-python/blob/main/src/agents/result.py#L136) |
| Google ADK | **Approach 2** [Emits events](https://google.github.io/adk-docs/runtime/#step-by-step-breakdown) with [FinalResponse](https://github.com/google/adk-java/blob/main/core/src/main/java/com/google/adk/events/Event.java#L232) true (Primary) / false (Secondary) and callers have to filter out those with false to get just the final response message | **Approach 2** Similar to non-streaming except [events](https://google.github.io/adk-docs/runtime/#streaming-vs-non-streaming-output-partialtrue) are emitted with [Partial](https://github.com/google/adk-java/blob/main/core/src/main/java/com/google/adk/events/Event.java#L133) true to indicate that they are streaming messages. A final non partial event is also emitted. |
| AWS (Strands) | **Approach 3** Returns an [AgentResult](https://strandsagents.com/docs/api/python/strands.agent.agent_result/) (Primary) with messages and a reason for the run's completion. | **Approach 2** [Streams events](https://strandsagents.com/docs/api/python/strands.agent.agent/) (Primary+Secondary) including, response text, current_tool_use, even data from "callbacks" (strands plugins) |
| AWS (Strands) | **Approach 3** Returns an [AgentResult](https://strandsagents.com/latest/documentation/docs/api-reference/python/agent/agent_result/) (Primary) with messages and a reason for the run's completion. | **Approach 2** [Streams events](https://strandsagents.com/latest/documentation/docs/api-reference/python/agent/agent/#strands.agent.agent.Agent.stream_async) (Primary+Secondary) including, response text, current_tool_use, even data from "callbacks" (strands plugins) |
| LangGraph | **Approach 2** A mixed list of all [messages](https://langchain-ai.github.io/langgraph/agents/run_agents/#output-format) | **Approach 2** A mixed list of all [messages](https://langchain-ai.github.io/langgraph/agents/run_agents/#output-format) |
| Agno | **Combination of various approaches** Returns a [RunResponse](https://docs.agno.com/reference/agents/run-response) object with text content, messages (essentially chat history including inputs and instructions), reasoning and thinking text properties. Secondary events could potentially be extracted from messages. | **Approach 2** Returns [RunResponseEvent](https://docs.agno.com/reference/agents/run-response#runresponseevent-types-and-attributes) objects including tool call, memory update, etc, information, where the [RunResponseCompletedEvent](https://docs.agno.com/reference/agents/run-response#runresponsecompletedevent) has similar properties to RunResponse|
| A2A | **Approach 3** Returns a [Task or Message](https://a2aproject.github.io/A2A/latest/specification/#71-messagesend) where the message is the final result (Primary) and task is a reference to a long running process. | **Approach 2** Returns a [stream](https://a2aproject.github.io/A2A/latest/specification/#72-messagestream) that contains task updates (Secondary) and a final message (Primary) |
@@ -496,7 +496,7 @@ We need to decide what AIContent types, each agent response type will be mapped
|-|-|
| AutoGen | **Approach 1** Supports [configuring an agent](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.html#structured-output) at agent creation. |
| Google ADK | **Approach 1** Both [input and output schemas can be specified for LLM Agents](https://google.github.io/adk-docs/agents/llm-agents/#structuring-data-input_schema-output_schema-output_key) at construction time. This option is specific to this agent type and other agent types do not necessarily support |
| AWS (Strands) | **Approach 2** Supports a special invocation method called [structured_output](https://strandsagents.com/docs/api/python/strands.agent.agent/) |
| AWS (Strands) | **Approach 2** Supports a special invocation method called [structured_output](https://strandsagents.com/latest/documentation/docs/api-reference/python/agent/agent/#strands.agent.agent.Agent.structured_output) |
| LangGraph | **Approach 1** Supports [configuring an agent](https://langchain-ai.github.io/langgraph/agents/agents/?h=structured#6-configure-structured-output) at agent construction time, and a [structured response](https://langchain-ai.github.io/langgraph/agents/run_agents/#output-format) can be retrieved as a special property on the agent response |
| Agno | **Approach 1** Supports [configuring an agent](https://docs.agno.com/input-output/structured-output/agent) at agent construction time |
| A2A | **Informal Approach 2** Doesn't formally support schema negotiation, but [hints can be provided via metadata](https://a2a-protocol.org/latest/specification/#97-structured-data-exchange-requesting-and-providing-json) at invocation time |
@@ -508,7 +508,7 @@ We need to decide what AIContent types, each agent response type will be mapped
|-|-|
| AutoGen | Supports a [stop reason](https://microsoft.github.io/autogen/stable/reference/python/autogen_agentchat.base.html#autogen_agentchat.base.TaskResult.stop_reason) which is a freeform text string |
| Google ADK | [No equivalent present](https://github.com/google/adk-python/blob/main/src/google/adk/events/event.py) |
| AWS (Strands) | Exposes a [stop_reason](https://strandsagents.com/docs/api/python/strands.types.event_loop/) property on the [AgentResult](https://strandsagents.com/docs/api/python/strands.agent.agent_result/) class with options that are tied closely to LLM operations. |
| AWS (Strands) | Exposes a [stop_reason](https://strandsagents.com/latest/documentation/docs/api-reference/python/types/event_loop/#strands.types.event_loop.StopReason) property on the [AgentResult](https://strandsagents.com/latest/documentation/docs/api-reference/python/agent/agent_result/) class with options that are tied closely to LLM operations. |
| LangGraph | No equivalent present, output contains only [messages](https://langchain-ai.github.io/langgraph/agents/run_agents/#output-format) |
| Agno | [No equivalent present](https://docs.agno.com/reference/agents/run-response) |
| A2A | No equivalent present, response only contains a [message](https://a2a-protocol.org/latest/specification/#64-message-object) or [task](https://a2a-protocol.org/latest/specification/#61-task-object). |
File diff suppressed because it is too large Load Diff
@@ -1,125 +0,0 @@
---
status: accepted
contact: rogerbarreto
date: 2026-03-06
deciders: rogerbarreto, alliscode
consulted: ""
informed: ""
---
# Foundry agent surface stays centered on `ChatClientAgent`
## Context
The Microsoft Foundry integration exposes two distinct usage patterns:
1. Direct Responses usage, where callers provide model, instructions, and tools at runtime.
2. Server-side versioned agents, where callers create and manage `AgentVersion` resources through `AIProjectClient.Agents`.
We briefly explored adding public wrapper types such as `FoundryAgent`, `FoundryVersionedAgent`, and `FoundryResponsesChatClient` to make those paths feel more specialized. That direction created extra public types, duplicated existing `ChatClientAgent` behavior, and pushed samples toward compatibility helpers instead of the native Azure SDK flow.
## Decision
Keep the public surface centered on `ChatClientAgent`.
- Direct Responses scenarios use `AIProjectClient.AsAIAgent(...)`.
- Server-side versioned scenarios use native `AIProjectClient.Agents` APIs to create or retrieve agent resources, then wrap `AgentRecord` or `AgentVersion` with `AIProjectClient.AsAIAgent(...)`.
- Compatibility helpers such as `AIProjectClient.CreateAIAgentAsync(...)` and `AIProjectClient.GetAIAgentAsync(...)` remain only as obsolete migration shims.
- Public wrapper types `FoundryAgent`, `FoundryVersionedAgent`, `FoundryResponsesChatClient`, and `FoundryResponsesChatClientAgent` are not part of the chosen direction.
## Why
- `ChatClientAgent` is already the framework abstraction used everywhere else.
- `AIProjectClient` is the native Azure SDK entry point for versioned agent lifecycle operations.
- A single agent abstraction avoids parallel type hierarchies for the same backend.
- Samples become clearer when they show either:
- direct Responses construction via `AIProjectClient.AsAIAgent(...)`, or
- native Foundry resource management via `AIProjectClient.Agents`.
## Consequences
### Direct Responses path
Use the convenience overloads on `AIProjectClient`:
```csharp
AIProjectClient aiProjectClient = new(new Uri(endpoint), credential);
ChatClientAgent agent = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are good at telling jokes.",
name: "JokerAgent");
```
Or use composed `ChatClientAgent`
```csharp
ProjectResponsesClient projectResponsesClient = new(new Uri(endpoint), new DefaultAzureCredential(), new AgentReference($"model:{deploymentName}"));
ChatClientAgent agent = new(
chatClient: projectResponsesClient.AsIChatClient(),
instructions: "You are good at telling jokes.",
name: "JokerAgent");
```
This path is code-first and does not create a persistent server-side agent.
### Versioned agent path
Use the convenience overloads on `AIProjectClient`:
```csharp
AIProjectClient aiProjectClient = new(new Uri(endpoint), credential);
AgentVersion version = await aiProjectClient.Agents.CreateAgentVersionAsync(
"JokerAgent",
new AgentVersionCreationOptions(
new PromptAgentDefinition(deploymentName)
{
Instructions = "You are good at telling jokes."
}));
ChatClientAgent agent = aiProjectClient.AsAIAgent(version);
```
Or use composed `ChatClientAgent`
```csharp
AIProjectClient aiProjectClient = new(new Uri(endpoint), credential);
AgentVersion version = await aiProjectClient.Agents.CreateAgentVersionAsync(
"JokerAgent",
new AgentVersionCreationOptions(
new PromptAgentDefinition(deploymentName)
{
Instructions = "You are good at telling jokes."
}));
ProjectResponsesClient projectResponsesClient = aiProjectClient
.GetProjectOpenAIClient()
.GetProjectResponsesClientForAgent(new AgentReference(version.Name, version.Version));
ChatClientAgent agent = new(
chatClient: projectResponsesClient.AsIChatClient(),
name: "JokerAgent");
```
### Samples
- `FoundryAgents/` samples show the direct Responses path with `AIProjectClient.AsAIAgent(...)`.
- `FoundryVersionedAgents/` samples should show native `AIProjectClient.Agents` create/get/delete flows plus `AsAIAgent(...)`.
### Compatibility APIs
Obsolete helper extensions remain only to ease migration of existing code. New samples and new guidance should not be written against them.
## Rejected direction
Do not introduce or preserve separate public wrapper types whose main purpose is to forward to `ChatClientAgent` while carrying Foundry-specific naming.
That approach:
- duplicates lifecycle concepts already present on `AIProjectClient`,
- fragments the public API,
- complicates samples and docs,
- and makes migration harder by encouraging wrapper-specific affordances.
@@ -1,815 +0,0 @@
---
status: accepted
contact: bentho
date: 2026-02-27
deciders: bentho, markwallace-microsoft, westey-m
consulted: Pratyush Mishra, Shivam Shrivastava, Manni Arora (Centrica eval scenario)
informed: Agent Framework team, Foundry Evals team
---
# Agent Evaluation Architecture with Azure AI Foundry Integration
## Context and Problem Statement
Azure AI Foundry provides a rich evaluation service for AI agents — built-in evaluators for agent behavior (task adherence, intent resolution), tool usage (tool call accuracy, tool selection), quality (coherence, fluency, relevance), and safety (violence, self-harm, prohibited actions). Results are viewable in the Foundry portal with dashboards and comparison views.
However, using Foundry Evals with an agent-framework agent today requires significant manual effort. Developers must:
1. Transform agent-framework's `Message`/`Content` types into the OpenAI-style agent message schema that Foundry evaluators expect
2. Map tool definitions from agent-framework's `FunctionTool` format to evaluator-compatible schemas
3. Manually wire up the correct Foundry data source type (`azure_ai_traces`, `jsonl`, `azure_ai_target_completions`, etc.) depending on their scenario
4. Handle App Insights trace ID queries, response ID collection, and eval polling
Additionally, evaluation is a concern that extends beyond any single provider. Developers may want to use local evaluators (LLM-as-judge, regex, keyword matching), third-party evaluation libraries, or multiple providers in combination. The architecture must support this without creating a Foundry-specific lock-in at the API level.
### Functional Requirements for Agent Evaluation
- **Single agents and workflows.** Evaluate both individual agent responses and multi-agent workflow results, with per-agent breakdown to pinpoint underperformance.
- **One-shot and multi-turn conversations.** Capture full conversation trajectories — including tool calls and results — not just final query/response pairs.
- **Conversation factoring.** Support splitting conversations into query/response in multiple ways (last turn, full trajectory, per-turn) because different factorings measure different things.
- **Multiple providers, mix and match.** Run Foundry LLM-as-judge evaluators alongside fast local checks and custom evaluators on the same data, without restructuring code.
- **Third-party extensibility.** Any evaluation library can participate by implementing the `Evaluator` protocol (Python) or `IAgentEvaluator` interface (.NET). No predetermined list of supported libraries — the protocol is intentionally simple (`evaluate(items) → results`) so that wrappers for libraries like DeepEval, RAGAS, or Promptfoo are straightforward to write.
- **Bring your own evaluator.** Creating a custom evaluator should be as simple as writing a function.
- **Evaluate without re-running.** Evaluate existing responses from logs or previous runs without invoking the agent again.
## Decision Drivers
- **Zero-friction evaluation**: Developers should go from "I have an agent" to "I have eval results" with minimal code.
- **Provider-agnostic API**: Core evaluation capabilities must not be tied to any specific provider. Provider configuration should be separate from the evaluation call.
- **Lowest concept count**: Introduce the fewest possible new types, abstractions, and APIs for developers to learn.
- **Leverage existing knowledge**: The framework already knows which agents exist, what tools they have, and what conversations occurred. Evals should use this automatically rather than requiring the developer to re-specify it.
- **Foundry-native results**: When using Foundry, results should be viewable in the Foundry portal with dashboards and comparison views.
- **Progressive disclosure**: Simple scenarios should be near-zero code. Advanced scenarios should build on the same primitives.
- **Cross-language parity**: Design must be implementable in both Python and .NET.
## Considered Options
1. **Provider-specific functions** — Build Foundry-specific helper functions (`evaluate_agent()`, etc.) directly in the Azure package. All eval functions take Foundry connection parameters.
2. **Evaluator protocol with shared orchestration** — Define a provider-agnostic `Evaluator` protocol in the base agent library (`agent_framework` in Python, `Microsoft.Agents.AI` in .NET). Orchestration functions live alongside it. Providers implement the protocol.
3. **Full eval framework** — Build comprehensive eval infrastructure including custom evaluator definitions, scoring profiles, and reporting inside agent-framework.
## Decision Outcome
Proposed option: "Evaluator protocol with shared orchestration", because it delivers the low-friction developer experience, supports multiple providers without API changes, and keeps the concept count low.
### Usage Examples
#### Evaluate an agent
The agent is invoked once per query by default. For statistically meaningful evaluation, provide multiple diverse queries. For measuring **consistency** (does the same query produce reliable results?), use `num_repetitions` to run each query N times independently:
**Python:**
```python
evals = FoundryEvals(
project_client=client,
model_deployment="gpt-4o",
evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)
results = await evaluate_agent(
agent=my_agent,
queries=[
"What's the weather in Seattle?",
"Plan a weekend trip to Portland",
"What restaurants are near Pike Place?",
],
evaluators=evals,
)
for r in results:
r.assert_passed()
```
**C#:**
```csharp
var evals = new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence);
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] {
"What's the weather in Seattle?",
"Plan a weekend trip to Portland",
"What restaurants are near Pike Place?",
},
evals);
results.AssertAllPassed();
```
`evaluate_agent` returns one `EvalResults` per evaluator. Each result contains per-item scores with the evaluated response for auditing:
```
# results[0] (FoundryEvals)
EvalResults(status="completed", passed=3, failed=0, total=3)
items[0]: EvalItemResult(
query="What's the weather in Seattle?",
response="It's currently 72°F and sunny in Seattle.",
scores={"relevance": 5, "coherence": 5})
items[1]: EvalItemResult(
query="Plan a weekend trip to Portland",
response="Here's a 2-day Portland itinerary...",
scores={"relevance": 4, "coherence": 5})
items[2]: EvalItemResult(
query="What restaurants are near Pike Place?",
response="Top restaurants near Pike Place Market: ...",
scores={"relevance": 5, "coherence": 4})
```
#### Measure consistency with repetitions
Run each query multiple times to detect non-deterministic behavior:
**Python:**
```python
results = await evaluate_agent(
agent=my_agent,
queries=["What's the weather in Seattle?"],
evaluators=evals,
num_repetitions=3, # each query runs 3 times independently
)
# results contain 3 items (1 query × 3 repetitions)
```
**C#:**
```csharp
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] { "What's the weather in Seattle?" },
evals,
numRepetitions: 3); // each query runs 3 times independently
// results contain 3 items (1 query × 3 repetitions)
```
#### Evaluate a response you already have
When you already have agent responses, pass them directly to skip re-running the agent. Each query is paired with its corresponding response:
**Python:**
```python
queries = ["What's the weather?", "What's the capital of France?"]
responses = [await agent.run([Message("user", [q])]) for q in queries]
results = await evaluate_agent(
responses=responses,
evaluators=evals,
)
```
**C#:**
```csharp
var queries = new[] { "What's the weather?" };
var responses = new List<AgentResponse>();
foreach (var q in queries)
responses.Add(await agent.RunAsync(new[] { new ChatMessage(ChatRole.User, q) }));
AgentEvaluationResults results = await agent.EvaluateAsync(
responses: responses,
evals);
```
Each `AgentResponse` already contains the conversation (query + response), so the evaluator extracts query/response from the conversation. When you pass `responses` without `queries`, the conversation is the source of truth.
#### Evaluate with conversation split strategies
By default, evaluators see only the last turn (final user message → final assistant response). For multi-turn conversations, you can control how the conversation is factored for evaluation:
**Python:**
```python
results = await evaluate_agent(
agent=agent,
queries=["Plan a 3-day trip to Paris"],
evaluators=evals,
conversation_split=ConversationSplit.FULL, # evaluate entire trajectory
)
# Or per-turn: each user→assistant exchange scored independently
results = await evaluate_agent(
agent=agent,
queries=["Plan a 3-day trip to Paris"],
evaluators=evals,
conversation_split=ConversationSplit.PER_TURN,
)
```
**C#:**
```csharp
// Full conversation as context
AgentEvaluationResults results = await agent.EvaluateAsync(
new[] { "Plan a 3-day trip to Paris" },
evals,
splitter: ConversationSplitters.Full);
// Per-turn splitting
var items = EvalItem.PerTurnItems(conversation); // one EvalItem per user turn
var results = await evals.EvaluateAsync(items);
```
With `PER_TURN`, a 3-turn conversation produces 3 scored items:
```
EvalResults(status="completed", passed=3, failed=0, total=3)
items[0]: query="Plan a 3-day trip to Paris" scores={"relevance": 5}
items[1]: query="What about restaurants?" scores={"relevance": 4}
items[2]: query="Make it budget-friendly" scores={"relevance": 5}
```
#### Evaluate a multi-agent workflow
**Python:**
```python
result = await workflow.run("Plan a trip to Paris")
eval_results = await evaluate_workflow(
workflow=workflow,
workflow_result=result,
evaluators=evals,
)
for r in eval_results:
print(f" overall: {r.passed}/{r.total}")
for name, sub in r.sub_results.items():
print(f" {name}: {sub.passed}/{sub.total}")
```
**C#:**
```csharp
WorkflowRunResult result = await workflow.RunAsync("Plan a trip to Paris");
IReadOnlyList<AgentEvaluationResults> evalResults = await result.EvaluateAsync(evals);
foreach (var r in evalResults)
{
Console.WriteLine($" overall: {r.Passed}/{r.Total}");
foreach (var (name, sub) in r.SubResults)
Console.WriteLine($" {name}: {sub.Passed}/{sub.Total}");
}
```
Workflows return one result per evaluator, with sub-results per agent in the workflow:
```
EvalResults(status="completed", passed=2, failed=0, total=2)
sub_results:
"planner": EvalResults(passed=1, total=1)
"researcher": EvalResults(passed=1, total=1)
```
#### Mix multiple providers
**Python:**
```python
@evaluator
def is_helpful(response: str) -> bool:
return len(response.split()) > 10
foundry = FoundryEvals(
project_client=client,
model_deployment="gpt-4o",
evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)
results = await evaluate_agent(
agent=agent,
queries=queries,
evaluators=[is_helpful, keyword_check("weather"), foundry],
)
```
**C#:**
```csharp
IReadOnlyList<AgentEvaluationResults> results = await agent.EvaluateAsync(
queries,
evaluators: new IAgentEvaluator[]
{
new LocalEvaluator(
EvalChecks.KeywordCheck("weather"),
FunctionEvaluator.Create("is_helpful", (string r) => r.Split(' ').Length > 10)),
new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence),
});
```
Multiple evaluators return one result each — `results[0]` is the local evaluator, `results[1]` is Foundry.
#### Custom function evaluators
**Python:**
```python
@evaluator
def mentions_city(response: str, expected_output: str) -> bool:
return expected_output.lower() in response.lower()
@evaluator
def used_tools(conversation: list, tools: list) -> float:
# ... scoring logic
return score
local = LocalEvaluator(mentions_city, used_tools)
```
`@evaluator` uses **parameter name injection** — the function's parameter names determine what data it receives from the `EvalItem`. Supported names: `query`, `response`, `expected`, `expected_tool_calls`, `conversation`, `tools`, `context`. Any combination is valid.
**C#:**
```csharp
var local = new LocalEvaluator(
FunctionEvaluator.Create("mentions_city",
(EvalItem item) => item.ExpectedOutput != null
&& item.Response.Contains(item.ExpectedOutput, StringComparison.OrdinalIgnoreCase)),
FunctionEvaluator.Create("is_concise",
(string response) => response.Split(' ').Length < 500));
```
## What To Build
### Core: Evaluator Protocol
A runtime-checkable protocol that any evaluation provider implements:
```python
@runtime_checkable
class Evaluator(Protocol):
name: str
async def evaluate(
self, items: Sequence[EvalItem], *, eval_name: str = "Agent Framework Eval"
) -> EvalResults: ...
```
The protocol is minimal — just `name` and `evaluate()`.
### Core: EvalItem
Provider-agnostic data format for items to evaluate:
```python
@dataclass
class ExpectedToolCall:
name: str # Tool/function name
arguments: dict[str, Any] | None = None # None = don't check args
@dataclass
class EvalItem:
conversation: list[Message] # Single source of truth
tools: list[FunctionTool] | None = None # Agent's available tools
context: str | None = None
expected_output: str | None = None # Ground-truth for comparison
expected_tool_calls: list[ExpectedToolCall] | None = None
split_strategy: ConversationSplitter | None = None
query: str # property — derived from conversation split
response: str # property — derived from conversation split
```
`conversation` is the single source of truth. `query` and `response` are derived properties — splitting the conversation at the last user message (default) and extracting text from each side. Changing the `split_strategy` consistently changes all derived values.
`tools` provides typed `FunctionTool` objects — including MCP tools, which are automatically extracted after agent runs.
### Internal: AgentEvalConverter
Internal class that converts agent-framework types to `EvalItem`. Used by `evaluate_agent()` and `evaluate_workflow()` — not part of the public API:
| Agent Framework | Eval Format |
|---|---|
| `Content.function_call` | `tool_call` in OpenAI chat format |
| `Content.function_result` | `tool_result` in OpenAI chat format |
| `FunctionTool` | `{name, description, parameters}` schema |
| `Message` history | `conversation` list + `query`/`response` extraction |
### Core: EvalResults
Rich result type with convenience properties for CI integration:
```python
results.all_passed # bool: no failures or errors (recursive for workflow)
results.passed # int: passing count
results.failed # int: failure count
results.total # int: total = passed + failed + errored
results.items # list[EvalItemResult]: per-item detail with query, response, and scores
results.error # str | None: error details on failure
results.sub_results # dict: per-agent breakdown (workflow evals)
results.report_url # str | None: portal link (Foundry)
results.assert_passed() # raises AssertionError with details
```
### Core: Orchestration Functions
Provider-agnostic functions that extract data and delegate to evaluators:
| Function | What it does |
|---|---|
| `evaluate_agent()` | Runs agent against test queries (or evaluates pre-existing `responses=`), converts to `EvalItem`s, passes to evaluator. Accepts optional `expected_output=` for ground-truth comparison, `expected_tool_calls=` for tool-correctness evaluation, and `num_repetitions=` for consistency measurement |
| `evaluate_workflow()` | Extracts per-agent data from `WorkflowRunResult`, evaluates each agent and overall output. Per-agent breakdown in `sub_results`. Also accepts `num_repetitions=` |
### Core: Conversation Split Strategies
Multi-turn conversations must be split into query (input) and response (output) halves for evaluation. How you split determines *what you're evaluating*:
**Last-turn split** — split at the last user message. Everything up to and including it is the query context; the agent's subsequent actions are the response:
```
conversation: user1 → assistant1 → user2 → assistant2(tool) → tool_result → assistant3
query_messages: [user1, assistant1, user2]
response_messages: [assistant2(tool), tool_result, assistant3]
```
This evaluates: "Given all the context so far, did the agent answer the latest question well?" Best for response quality at a specific point in the conversation.
**Full-conversation split** — the first user message is the query; everything after is the response:
```
query_messages: [user1]
response_messages: [assistant1, user2, assistant2(tool), tool_result, assistant3]
```
This evaluates: "Given the original request, did the entire conversation trajectory serve the user?" Best for task completion and overall conversation quality.
**Per-turn split** — produces N eval items from an N-turn conversation. Each turn is evaluated with its cumulative context:
```
item 1: query = [user1], response = [assistant1]
item 2: query = [user1, assistant1, user2], response = [assistant2(tool), tool_result, assistant3]
```
This evaluates each response independently. Best for fine-grained analysis and pinpointing where a conversation goes wrong.
These factorings produce different scores for the same conversation. The framework ships all three as built-in strategies, defaulting to last-turn. Developers can also provide a custom splitter — a function (Python) or `IConversationSplitter` implementation (.NET) — and override the strategy at the call site or per evaluator.
### Azure AI: FoundryEvals
`Evaluator` implementation backed by Azure AI Foundry:
```python
class FoundryEvals:
def __init__(self, *, project_client=None, openai_client=None,
model_deployment: str, evaluators=None, ...)
async def evaluate(self, items, *, eval_name) -> EvalResults
```
**Smart auto-detection in `evaluate()`:**
- Default evaluators: relevance, coherence, task_adherence
- Auto-adds `tool_call_accuracy` when items have tools/`tool_definitions`
- Filters out tool evaluators for items without tools
### Azure AI: FoundryEvals Constants
```python
from agent_framework_azure_ai import FoundryEvals
evaluators = [FoundryEvals.RELEVANCE, FoundryEvals.TOOL_CALL_ACCURACY]
```
Categories: Agent behavior, Tool usage, Quality, Safety.
### Azure AI: Foundry-Specific Functions
| Function | What it does |
|---|---|
| `evaluate_traces()` | Evaluate from stored response IDs or OTel traces |
| `evaluate_foundry_target()` | Evaluate a Foundry-registered agent or deployment |
### Core: LocalEvaluator and Function Evaluators
`LocalEvaluator` implements the `Evaluator` protocol for fast, API-free evaluation. It runs check functions locally — useful for inner-loop development, CI smoke tests, and combining with cloud-based evaluators.
Built-in checks:
- `keyword_check(*keywords)` — response must contain specified keywords
- `tool_called_check(*tool_names)` — agent must have called specified tools
- `tool_calls_present` — all `expected_tool_calls` names appear in conversation (unordered, extras OK)
- `tool_call_args_match` — expected tool calls match on name + arguments (subset match on args)
Custom function evaluators use `@evaluator` to wrap plain Python functions. The function's **parameter names** determine what data it receives from the `EvalItem`:
```python
from agent_framework import evaluator, LocalEvaluator
# Tier 1: Simple check — just query + response
@evaluator
def is_concise(response: str) -> bool:
return len(response.split()) < 500
# Tier 2: Ground truth — compare against expected output
@evaluator
def mentions_city(response: str, expected_output: str) -> bool:
return expected_output.lower() in response.lower()
# Tier 3: Full context — inspect conversation and tools
@evaluator
def used_tools(conversation: list, tools: list) -> float:
# ... scoring logic
return score
local = LocalEvaluator(is_concise, mentions_city, used_tools)
```
Supported parameters: `query`, `response`, `expected`, `expected_tool_calls`, `conversation`, `tools`, `context`.
Return types: `bool`, `float` (≥0.5 = pass), `dict` with `score` or `passed` key, or `CheckResult`.
Async functions are handled automatically — `@evaluator` detects `async def` and produces the right wrapper.
### Example: GAIA Benchmark
[GAIA](https://huggingface.co/gaia-benchmark) tests real-world multi-step tasks with known expected answers. Each task has a question and a ground-truth answer, with optional file attachments. The framework accommodates GAIA's knobs (difficulty levels, file inputs, multi-step tool use) through the existing `EvalItem` fields:
```python
from datasets import load_dataset
from agent_framework import evaluate_agent, evaluator, LocalEvaluator
gaia = load_dataset("gaia-benchmark/GAIA", "2023_level1", split="test")
@evaluator
def exact_match(response: str, expected_output: str) -> bool:
return expected_output.strip().lower() in response.strip().lower()
# Simple path — evaluate_agent handles running + expected_output stamping
results = await evaluate_agent(
agent=agent,
queries=[task["Question"] for task in gaia],
expected_output=[task["Final answer"] for task in gaia],
evaluators=LocalEvaluator(exact_match),
)
```
### Package Location
- Core types and orchestration: `agent_framework._eval`, `agent_framework._local_eval` (Python), `Microsoft.Agents.AI` (.NET)
- Foundry provider: `agent_framework_azure_ai._foundry_evals` (Python), `Microsoft.Agents.AI.AzureAI` (.NET)
- Azure-AI re-exports core types for convenience (Python)
## Known Limitations
1. **Tool evaluators require query + agent**: Tool evaluators need tool definition schemas. When using these evaluators with `evaluate_agent(responses=...)`, provide `queries=` and pass an agent with tool definitions.
2. **`model_deployment` always required**: Could potentially be inferred from the Foundry project configuration.
## Open Questions
1. **Red teaming non-registered agents**: Requires Foundry API support for callback-based flows.
2. **Datasets with expected outputs**: A dataset abstraction for pre-populating `expected_output` values across eval runs is a natural next step but not yet designed.
3. **Multi-modal evaluation**: The `conversation` field on `EvalItem` already stores full `Message`/`Content` (Python) and `ChatMessage` (.NET) objects, which can represent multi-modal content (images, audio, structured data). Evaluators that accept the full `EvalItem` or `conversation` parameter can access this content today. However, the convenience shortcuts — `query`/`response` string projections and the `FunctionEvaluator` string overloads — are text-only. Multi-modal-aware evaluators should use the full-item path (`Func<EvalItem, CheckResult>` in .NET, `conversation: list` parameter in Python).
## .NET Implementation Design
### Key Difference: MEAI Ecosystem
Unlike Python, the .NET ecosystem already has `Microsoft.Extensions.AI.Evaluation` (v10.3.0) providing:
- `IEvaluator` — per-item evaluation of `(messages, chatResponse) → EvaluationResult`
- `CompositeEvaluator` — combines multiple evaluators
- Quality evaluators — `RelevanceEvaluator`, `CoherenceEvaluator`, `GroundednessEvaluator`
- Safety evaluators — `ContentHarmEvaluator`, `ProtectedMaterialEvaluator`
- Metric types — `NumericMetric`, `BooleanMetric`, `StringMetric`
The .NET integration uses MEAI's `IEvaluator` directly — no new evaluator interface. Our contribution is the **orchestration layer**: extension methods that run agents, extract data, call `IEvaluator` per item, and aggregate results.
### Architecture
```
┌──────────────────────────────────────────────────────────────┐
│ Developer Code │
│ agent.EvaluateAsync(queries, evaluator) │
│ run.EvaluateAsync(evaluator) │
└────────────────┬─────────────────────────────────────────────┘
┌────────────────▼─────────────────────────────────────────────┐
│ Orchestration Layer (Microsoft.Agents.AI) │
│ AgentEvaluationExtensions — runs agents, extracts data, │
│ calls IEvaluator per item, aggregates into │
│ AgentEvaluationResults │
└────────────────┬─────────────────────────────────────────────┘
│ IEvaluator (MEAI)
┌───────────┼────────────┐
│ │ │
┌───▼───-┐ ┌───▼────┐ ┌────▼──────────┐
│ MEAI │ │ Local │ │ Foundry │
│ Quality│ │ Checks │ │ (cloud batch) │
│ Safety │ │ Lambdas│ │ │
└────────┘ └────────┘ └───────────────┘
```
All evaluators implement MEAI's `IEvaluator`. The orchestration layer doesn't need to know which kind — it calls `EvaluateAsync(messages, chatResponse)` per item on all of them. `FoundryEvals` handles batching internally (buffers items, submits once, returns per-item results).
### .NET Core Types
**No new evaluator interface.** Use MEAI's `IEvaluator` directly.
**`AgentEvaluationResults`** — The only new type. Aggregates per-item MEAI `EvaluationResult`s across a batch of queries:
```csharp
public class AgentEvaluationResults
{
public string Provider { get; init; }
public string? ReportUrl { get; init; }
// Per-item — standard MEAI EvaluationResult, unchanged
public IReadOnlyList<EvaluationResult> Items { get; init; }
// Aggregate pass/fail derived from metric interpretations
public int Passed { get; }
public int Failed { get; }
public int Total { get; }
public bool AllPassed { get; }
// Workflow: per-agent breakdown
public IReadOnlyDictionary<string, AgentEvaluationResults>? SubResults { get; init; }
public void AssertAllPassed(string? message = null);
}
```
### .NET Evaluator Implementations
All implement MEAI's `IEvaluator`:
**`LocalEvaluator`** — Runs lambda checks locally, returns `BooleanMetric` per check:
```csharp
var local = new LocalEvaluator(
FunctionEvaluator.Create("is_concise",
(string response) => response.Split().Length < 500),
EvalChecks.KeywordCheck("weather"),
EvalChecks.ToolCalledCheck("get_weather"));
```
**MEAI evaluators** — Used directly, no adapter needed:
```csharp
var quality = new CompositeEvaluator(
new RelevanceEvaluator(),
new CoherenceEvaluator());
```
**`FoundryEvals`** — Implements `IEvaluator` but batches internally. On first call, buffers the item. On the last item (or when explicitly flushed), submits the batch to Foundry and distributes per-item results:
```csharp
var foundry = new FoundryEvals(projectClient, "gpt-4o");
```
### .NET Orchestration: Extension Methods
```csharp
public static class AgentEvaluationExtensions
{
// Evaluate an agent against test queries
public static Task<AgentEvaluationResults> EvaluateAsync(
this AIAgent agent,
IEnumerable<string> queries,
IEvaluator evaluator,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate pre-existing responses (without re-running the agent)
public static Task<AgentEvaluationResults> EvaluateAsync(
this AIAgent agent,
AgentResponse responses,
IEvaluator evaluator,
IEnumerable<string>? queries = null,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate with multiple evaluators (one result per evaluator)
public static Task<IReadOnlyList<AgentEvaluationResults>> EvaluateAsync(
this AIAgent agent,
IEnumerable<string> queries,
IEnumerable<IEvaluator> evaluators,
ChatConfiguration? chatConfiguration = null,
IEnumerable<string>? expectedOutput = null,
CancellationToken cancellationToken = default);
// Evaluate a workflow run with per-agent breakdown
public static Task<AgentEvaluationResults> EvaluateAsync(
this Run run,
IEvaluator evaluator,
ChatConfiguration? chatConfiguration = null,
bool includeOverall = true,
bool includePerAgent = true,
CancellationToken cancellationToken = default);
}
```
**Usage:**
```csharp
// MEAI evaluators — just works
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new RelevanceEvaluator(),
chatConfiguration: new ChatConfiguration(evalClient));
// Local checks
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new LocalEvaluator(
EvalChecks.KeywordCheck("weather")));
// Foundry cloud
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
// Evaluate existing response (without re-running the agent)
var response = await agent.RunAsync("What's the weather?");
var results = await agent.EvaluateAsync(
responses: response,
queries: ["What's the weather?"],
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
// Mixed — one result per evaluator
var results = await agent.EvaluateAsync(
queries: ["What's the weather?"],
evaluators: [
new LocalEvaluator(EvalChecks.KeywordCheck("weather")),
new RelevanceEvaluator(),
new FoundryEvals(projectClient, "gpt-4o")
],
chatConfiguration: new ChatConfiguration(evalClient));
// Workflow with per-agent breakdown
Run run = await workflowRunner.RunAsync(workflow, "Plan a trip");
var results = await run.EvaluateAsync(
evaluator: new FoundryEvals(projectClient, "gpt-4o"));
```
### .NET Function Evaluators
Typed factory overloads (C# equivalent of Python's `@evaluator`):
```csharp
public static class FunctionEvaluator
{
public static EvalCheck Create(string name, Func<string, bool> check); // response only
public static EvalCheck Create(string name, Func<string, string?, bool> check); // expectedOutput
public static EvalCheck Create(string name, Func<EvalItem, bool> check); // full item
public static EvalCheck Create(string name, Func<EvalItem, CheckResult> check); // full control
public static EvalCheck Create(string name, Func<string, Task<bool>> check); // async
}
```
`EvalItem` is a lightweight record used only by `FunctionEvaluator` and `LocalEvaluator` to pass context to check functions. It is not part of the `IEvaluator` interface:
```csharp
public record ExpectedToolCall(string Name, IReadOnlyDictionary<string, object>? Arguments = null);
public sealed class EvalItem
{
public EvalItem(string query, string response, IReadOnlyList<ChatMessage> conversation);
public string Query { get; }
public string Response { get; }
public IReadOnlyList<ChatMessage> Conversation { get; }
public IReadOnlyList<AITool>? Tools { get; set; }
public string? ExpectedOutput { get; set; }
public IReadOnlyList<ExpectedToolCall>? ExpectedToolCalls { get; set; }
public string? Context { get; set; }
public IConversationSplitter? Splitter { get; set; }
}
```
### Workflow Data Extraction (.NET)
`run.EvaluateAsync()` walks `Run.OutgoingEvents` via LINQ:
1. Pair `ExecutorInvokedEvent` / `ExecutorCompletedEvent` by `ExecutorId`
2. Extract `AgentResponseEvent` for per-agent `ChatResponse`
3. Call `evaluator.EvaluateAsync()` per invocation
4. Group by `ExecutorId` for per-agent `SubResults`
5. Use final workflow output for overall eval
### .NET Package Structure
| Package | Contents |
|---------|----------|
| `Microsoft.Agents.AI` | `IAgentEvaluator`, `AgentEvaluationResults`, `LocalEvaluator`, `FunctionEvaluator`, `EvalChecks`, `EvalItem`, `ExpectedToolCall`, `AgentEvaluationExtensions` |
| `Microsoft.Agents.AI.AzureAI` | `FoundryEvals` (provider + constants) |
### Python ↔ .NET Mapping
| Python | .NET |
|--------|------|
| `Evaluator` protocol | `IAgentEvaluator` (our interface; MEAI provides `IEvaluator` for per-item scoring) |
| `EvalItem` dataclass | `EvalItem` class |
| `EvalResults` | `AgentEvaluationResults` |
| `EvalItemResult` / `EvalScoreResult` | MEAI `EvaluationResult` / `EvaluationMetric` (reused) |
| `LocalEvaluator` | `LocalEvaluator` (implements `IAgentEvaluator`) |
| `@evaluator` | `FunctionEvaluator.Create()` overloads |
| `keyword_check()` / `tool_called_check()` | `EvalChecks.KeywordCheck()` / `EvalChecks.ToolCalledCheck()` |
| `tool_calls_present` / `tool_call_args_match` | (custom `FunctionEvaluator` — same pattern) |
| `ExpectedToolCall` dataclass | `ExpectedToolCall` record |
| `FoundryEvals` | `FoundryEvals` (implements `IAgentEvaluator`, includes evaluator name constants) |
| `evaluate_agent()` | `agent.EvaluateAsync(queries, evaluator)` extension method |
| `evaluate_agent(responses=)` | `agent.EvaluateAsync(responses, evaluator)` extension method |
| `evaluate_workflow()` | `run.EvaluateAsync()` extension method |
## More Information
- [Foundry Evals documentation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-approach-gen-ai) — Azure AI Foundry evaluation overview
-960
View File
@@ -1,960 +0,0 @@
status: proposed
date: 2026-03-23
contact: sergeymenshykh
deciders: rbarreto, westey-m, eavanvalkenburg
---
# Agent Skills: Multi-Source Architecture
## Context and Problem Statement
The Agent Framework needs a skills system that lets agents discover and use domain-specific knowledge, reference documents, and executable scripts. Skills can originate from different sources — filesystem directories (SKILL.md files), inline C# code, or reusable class libraries — and the framework must support all three uniformly while allowing extensibility, composition, and filtering.
## Decision Drivers
- Skills must be definable from multiple sources: filesystem, inline code, reusable classes, etc
- Common abstractions are needed so the provider and builder work uniformly regardless of skill origin
- File-based scripts must support user-defined executors, enabling custom runtimes and languages; code/class-based scripts execute in-process as C# delegates
- Skills must be filterable so consumers can include or exclude specific skills based on defined criteria
- Multiple skill sources must be composable into a single provider
- It must be possible to add custom skill sources (e.g., databases, REST APIs, package registries) by implementing a common abstraction
## Architecture
### Model-Facing Tools
Skills are presented to the model as up to three tools that progressively disclose skill content. The system prompt lists available skill names and descriptions; the model then calls these tools on demand:
- **`load_skill(skillName)`** — returns the full skill body (instructions, listed resources, listed scripts)
- **`read_skill_resource(skillName, resourceName)`** — reads a supplementary resource (file-based or code-defined) associated with a skill
- **`run_skill_script(skillName, scriptName, arguments?)`** — executes a script associated with a skill; only registered when at least one skill contains scripts
Each tool delegates to the corresponding method on the resolved `AgentSkill` — calling `Resource.ReadAsync()` or `Script.RunAsync()` respectively.
If skills have no scripts defined, the `run_skill_script` tool is **not advertised** to the model and instructions related to script execution are **not included** in the default skills instructions.
### Abstract Base Types
The architecture defines four abstract base types that all skill variants implement:
```csharp
public abstract class AgentSkill
{
public abstract AgentSkillFrontmatter Frontmatter { get; }
public abstract string Content { get; }
public abstract IReadOnlyList<AgentSkillResource>? Resources { get; }
public abstract IReadOnlyList<AgentSkillScript>? Scripts { get; }
}
public abstract class AgentSkillResource
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default);
}
public abstract class AgentSkillScript
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, CancellationToken cancellationToken = default);
}
public abstract class AgentSkillsSource
{
public abstract Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default);
}
```
Skill metadata is captured via `AgentSkillFrontmatter`:
```csharp
public sealed class AgentSkillFrontmatter
{
public AgentSkillFrontmatter(string name, string description) { ... }
public string Name { get; }
public string Description { get; }
public string? License { get; set; }
public string? Compatibility { get; set; }
public string? AllowedTools { get; set; }
public AdditionalPropertiesDictionary? Metadata { get; set; }
}
```
The type hierarchy at a glance:
```
AgentSkill (abstract) AgentSkillsSource (abstract)
├── AgentFileSkill ├── AgentFileSkillsSource (public)
└── [Programmatic] ├── AgentInMemorySkillsSource (public)
├── AgentInlineSkill ├── AggregatingAgentSkillsSource (public)
└── AgentClassSkill (abstract) └── DelegatingAgentSkillsSource (abstract, public)
├── FilteringAgentSkillsSource (public)
AgentSkillResource (abstract) ├── CachingAgentSkillsSource (public)
├── AgentFileSkillResource └── DeduplicatingAgentSkillsSource (public)
└── AgentInlineSkillResource
AgentSkillScript (abstract)
├── AgentFileSkillScript
└── AgentInlineSkillScript
```
There are two top-level categories of skills:
1. **File-Based Skills** — discovered from `SKILL.md` files on the filesystem. Resources and scripts are files in subdirectories.
2. **Programmatic Skills** — defined in C# code. These are further divided into:
- **Inline Skills** — built at runtime via the `AgentInlineSkill` class and its fluent API. Ideal for quick, agent-specific skill definitions.
- **Class-Based Skills** — defined as reusable C# classes that subclass `AgentClassSkill`. Ideal for packaging skills as shared libraries or NuGet packages.
Both programmatic skill types use `AgentInlineSkillResource` and `AgentInlineSkillScript` for their resources and scripts. They are typically served by `AgentInMemorySkillsSource`, which accepts any `AgentSkill` and is not limited to programmatic skills.
### File-Based Skills
File-based skills are authored as `SKILL.md` files on disk. Resources and scripts are discovered from corresponding subfolders within the skill directory.
**`AgentFileSkill`** — A filesystem-based skill discovered from a directory containing a `SKILL.md` file. Parsed from YAML frontmatter; content is the raw markdown body. Resources and scripts are discovered from files in corresponding subfolders:
```csharp
public sealed class AgentFileSkill : AgentSkill
{
internal AgentFileSkill(
AgentSkillFrontmatter frontmatter, string content, string path,
IReadOnlyList<AgentSkillResource>? resources = null,
IReadOnlyList<AgentSkillScript>? scripts = null) { ... }
}
```
**`AgentFileSkillResource`** — A file-based skill resource. Reads content from a file on disk relative to the skill directory:
```csharp
internal sealed class AgentFileSkillResource : AgentSkillResource
{
public AgentFileSkillResource(string name, string fullPath) { ... }
public string FullPath { get; }
public override Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return File.ReadAllTextAsync(FullPath, Encoding.UTF8, cancellationToken);
}
}
```
**`AgentFileSkillScript`** — A file-based skill script that represents a script file on disk. Delegates execution to an external `AgentFileSkillScriptRunner` callback (e.g., runs Python/shell via `Process.Start`). Throws `NotSupportedException` if no executor is configured:
```csharp
public delegate Task<object?> AgentFileSkillScriptRunner(
AgentFileSkill skill, AgentFileSkillScript script,
AIFunctionArguments arguments, CancellationToken cancellationToken);
public sealed class AgentFileSkillScript : AgentSkillScript
{
private readonly AgentFileSkillScriptRunner _executor;
internal AgentFileSkillScript(string name, string fullPath, AgentFileSkillScriptRunner executor)
: base(name) { ... }
public override async Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, ...)
{
return await _executor(fileSkill, this, arguments, cancellationToken);
}
}
```
The executor can be provided at the **provider level** via `AgentSkillsProviderBuilder.UseFileScriptRunner(executor)` and optionally overridden for a **particular file skill** or for a **set of skills** at the file skill source level, giving fine-grained control over how different scripts are executed.
**`AgentFileSkillsSource`** — A skill source that discovers skills from filesystem directories containing `SKILL.md` files. Recursively scans directories (max 2 levels), validates frontmatter, and enforces path traversal and symlink security checks:
```csharp
public sealed partial class AgentFileSkillsSource : AgentSkillsSource
{
public AgentFileSkillsSource(
IEnumerable<string> skillPaths,
AgentFileSkillScriptRunner scriptRunner,
AgentFileSkillsSourceOptions? options = null,
ILoggerFactory? loggerFactory = null) { ... }
}
```
**`AgentFileSkillsSourceOptions`** — Configuration options for `AgentFileSkillsSource`. Allows customizing the allowed file extensions for resources and scripts without adding constructor parameters:
```csharp
public sealed class AgentFileSkillsSourceOptions
{
public IEnumerable<string>? AllowedResourceExtensions { get; set; }
public IEnumerable<string>? AllowedScriptExtensions { get; set; }
}
```
**Example** — A file-based skill on disk and how it is added to a source:
```
skills/
└── unit-converter/
├── SKILL.md # frontmatter + instructions
├── resources/
│ └── conversion-table.csv # discovered as a resource
└── scripts/
└── convert.py # discovered as a script
```
```csharp
var source = new AgentFileSkillsSource(skillPaths: ["./skills"], scriptRunner: SubprocessScriptRunner.RunAsync);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
### Programmatic Skills
Programmatic skills are defined in C# code rather than discovered from the filesystem. There are two kinds: **inline** and **class-based**. Both use `AgentInlineSkillResource` and `AgentInlineSkillScript` for resources and scripts, and are held by a single `AgentInMemorySkillsSource`.
**`AgentInMemorySkillsSource`** — A general-purpose skill source that holds any `AgentSkill` instances in memory. Although commonly used for programmatic skills (`AgentInlineSkill` and `AgentClassSkill`), it accepts any `AgentSkill` subclass and is not restricted to code-defined skills:
```csharp
public sealed class AgentInMemorySkillsSource : AgentSkillsSource
{
public AgentInMemorySkillsSource(
IEnumerable<AgentSkill> skills,
ILoggerFactory? loggerFactory = null) { ... }
}
```
#### Inline Skills
Inline skills are built at runtime via the `AgentInlineSkill` class and its fluent API. They are ideal for quick, agent-specific skill definitions where a full class hierarchy would be overkill.
**`AgentInlineSkill`** — A skill defined entirely in code. Resources can be static values or functions; scripts are always functions. Constructed with name, description, and instructions, then extended with resources and scripts:
```csharp
public sealed class AgentInlineSkill : AgentSkill
{
public AgentInlineSkill(string name, string description, string instructions, string? license = null, string? compatibility = null, ...) { ... }
public AgentInlineSkill(AgentSkillFrontmatter frontmatter, string instructions) { ... }
public AgentInlineSkill AddResource(object value, string name, string? description = null);
public AgentInlineSkill AddResource(Delegate handler, string name, string? description = null);
public AgentInlineSkill AddScript(Delegate handler, string name, string? description = null);
}
```
**`AgentInlineSkillResource`** — A skill resource that wraps a static value:
```csharp
public sealed class AgentInlineSkillResource : AgentSkillResource
{
public AgentInlineSkillResource(object value, string name, string? description = null)
: base(name, description)
{
_value = value;
}
public override Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return Task.FromResult<object?>(_value);
}
}
```
**`AgentInlineSkillResource`** — A skill resource backed by a delegate. The delegate is invoked via an `AIFunction` each time `ReadAsync` is called, producing a dynamic (computed) value:
```csharp
public sealed class AgentInlineSkillResource : AgentSkillResource
{
public AgentInlineSkillResource(Delegate handler, string name, string? description = null)
: base(name, description)
{
_function = AIFunctionFactory.Create(handler, name: name);
}
public override async Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default)
{
return await _function.InvokeAsync(new AIFunctionArguments() { Services = serviceProvider }, cancellationToken);
}
}
```
**`AgentInlineSkillScript`** — A skill script backed by a delegate via an `AIFunction`:
```csharp
public sealed class AgentInlineSkillScript : AgentSkillScript
{
private readonly AIFunction _function;
public AgentInlineSkillScript(Delegate handler, string name, string? description = null)
: base(name, description)
{
_function = AIFunctionFactory.Create(handler, name: name);
}
public JsonElement? ParametersSchema => _function.JsonSchema;
public override async Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, ...)
{
return await _function.InvokeAsync(arguments, cancellationToken);
}
}
```
**Example** — Creating an inline skill with a resource and script, then adding it to a source:
```csharp
var skill = new AgentInlineSkill(
name: "unit-converter",
description: "Converts between measurement units.",
instructions: """
Use this skill to convert values between metric and imperial units.
Refer to the conversion-table resource for supported unit pairs.
Run the convert script to perform conversions.
"""
)
.AddResource("kg=2.205lb, m=3.281ft, L=0.264gal", "conversion-table", "Supported unit pairs")
.AddScript(Convert, "convert", "Converts a value between units");
var source = new AgentInMemorySkillsSource([skill]);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
static string Convert(double value, double factor)
=> JsonSerializer.Serialize(new { result = Math.Round(value * factor, 4) });
```
#### Class-Based Skills
Class-based skills are designed for packaging skills as reusable libraries. Users subclass `AgentClassSkill` and override properties. Unlike inline skills, class-based skills are self-contained, can live in shared libraries or NuGet packages, and are well-suited for dependency injection.
**`AgentClassSkill`** — An abstract base class for defining skills as reusable C# classes that bundle all skill components (frontmatter, instructions, resources, scripts) together. Designed for packaging skills as distributable libraries:
```csharp
public abstract class AgentClassSkill : AgentSkill
{
public abstract string Instructions { get; }
// Content is auto-synthesized from Frontmatter + Instructions + Resources + Scripts
public override string Content =>
SkillContentBuilder.BuildContent(Frontmatter.Name, Frontmatter.Description,
SkillContentBuilder.BuildBody(Instructions, Resources, Scripts));
}
```
**Example** — Defining a class-based skill and adding it to a source:
```csharp
public class UnitConverterSkill : AgentClassSkill
{
public override AgentSkillFrontmatter Frontmatter { get; } =
new("unit-converter", "Converts between measurement units.");
public override string Instructions => """
Use this skill to convert values between metric and imperial units.
Refer to the conversion-table resource for supported unit pairs.
Run the convert script to perform conversions.
""";
public override IReadOnlyList<AgentSkillResource>? Resources { get; } =
[
new AgentInlineSkillResource("kg=2.205lb, m=3.281ft", "conversion-table"),
];
public override IReadOnlyList<AgentSkillScript>? Scripts { get; } =
[
new AgentInlineSkillScript(Convert, "convert"),
];
private static string Convert(double value, double factor)
=> JsonSerializer.Serialize(new { result = Math.Round(value * factor, 4) });
}
var source = new AgentInMemorySkillsSource([new UnitConverterSkill()]);
var provider = new AgentSkillsProvider(source);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
## Filtering, Caching, and Deduplication
The following subsections present alternative approaches for handling filtering, caching, and deduplication of skills across multiple sources.
### Via Composition
In this approach, the `AgentSkillsProvider` accepts a **single** `AgentSkillsSource`. Multiple sources are composed externally via an aggregate source, and cross-cutting concerns like filtering, caching, and deduplication are implemented as **source decorators** — subclasses of `DelegatingAgentSkillsSource` that intercept `GetSkillsAsync()`.
**`FilteringAgentSkillsSource`** — A decorator that applies filter logic before returning results. The decorator pattern keeps filtering orthogonal to source implementations and allows composing multiple filters:
```csharp
public sealed class FilteringAgentSkillsSource : DelegatingAgentSkillsSource
{
private readonly Func<AgentSkill, bool> _predicate;
public FilteringAgentSkillsSource(AgentSkillsSource innerSource, Func<AgentSkill, bool> predicate)
: base(innerSource)
{
_predicate = predicate;
}
public override async Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default)
{
var skills = await this.InnerSource.GetSkillsAsync(cancellationToken);
return skills.Where(_predicate).ToList();
}
}
```
**`CachingAgentSkillsSource`** — A decorator that caches skills after the first load, keeping the provider stateless and giving consumers control over caching granularity per source. For example, file-based skills (expensive to discover) can be cached while code-defined skills remain uncached:
```csharp
public sealed class CachingAgentSkillsSource : DelegatingAgentSkillsSource
{
private IList<AgentSkill>? _cached;
public CachingAgentSkillsSource(AgentSkillsSource innerSource)
: base(innerSource)
{
}
public override async Task<IList<AgentSkill>> GetSkillsAsync(CancellationToken cancellationToken = default)
{
return _cached ??= await this.InnerSource.GetSkillsAsync(cancellationToken);
}
}
```
**Deduplication** is similarly implemented as a decorator (`DeduplicatingAgentSkillsSource`) that deduplicates by name (case-insensitive, first-one-wins) and logs a warning for skipped duplicates.
**Example** — Combining file-based and code-defined sources with filtering and caching:
```csharp
var fileSource = new CachingAgentSkillsSource(new AgentFileSkillsSource(["./skills"]));
var codeSource = new AgentInMemorySkillsSource([myCodeSkill]);
var compositeSource = new FilteringAgentSkillsSource(
new AggregatingAgentSkillsSource([fileSource, codeSource]),
filter: s => s.Frontmatter.Name != "internal");
var provider = new AgentSkillsProvider(compositeSource);
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
**Pros:**
- Clean single-responsibility: the provider serves skills, sources provide them.
- Caching, filtering, and deduplication are composable as source decorators — each concern is a separate, testable wrapper.
**Cons:**
- DI is less flexible: multiple `AgentSkillsSource` implementations registered in the container cannot be auto-injected into the provider. The consumer must manually compose them via an aggregate source.
- Increased public API surface: requires additional public classes (aggregate source, caching decorators, filtering decorators) that consumers need to learn and use.
### Via AgentSkillsProvider
In this approach, the `AgentSkillsProvider` accepts **`IEnumerable<AgentSkillsSource>`** and handles aggregation, filtering, caching, and deduplication internally.
The provider aggregates skills from all registered sources, deduplicates by name (case-insensitive, first-one-wins), caches the result after the first load, and optionally applies filtering via a predicate on `AgentSkillsProviderOptions`. Duplicate skill names are logged as warnings.
**Example** — Registering multiple sources directly with the provider:
```csharp
// Conceptual example — in practice, use AgentSkillsProviderBuilder
var fileSource = new AgentFileSkillsSource(["./skills"]);
var codeSource = new AgentInMemorySkillsSource([myCodeSkill]);
var provider = new AgentSkillsProvider(
sources: [fileSource, codeSource],
options: new AgentSkillsProviderOptions
{
Filter = s => s.Frontmatter.Name != "internal",
});
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
**Pros:**
- DI-friendly: register multiple `AgentSkillsSource` implementations in the container, and they are all auto-injected into `AgentSkillsProvider` via `IEnumerable<AgentSkillsSource>`.
- Smaller public API surface: no need for aggregate source, caching decorators, or filtering decorator classes — these concerns are handled internally by the provider.
**Cons:**
- The provider takes on multiple responsibilities — aggregation, caching, deduplication, and filtering.
- Less granular caching control: caching is all-or-nothing across sources rather than per-source as with decorators.
- Less extensible: new behaviors (e.g., ordering, TTL expiration) require modifying the provider rather than adding a decorator.
### Builder Pattern
**`AgentSkillsProviderBuilder`** provides a fluent API for composing skills from multiple sources. The builder centralizes configuration — script executors, approval callbacks, prompt templates, and filtering — so consumers don't need to know the underlying source types.
The builder internally decides how to wire up the object graph: it creates the appropriate source instances, applies caching and filtering, and returns a fully configured `AgentSkillsProvider`. This keeps the setup code concise while still allowing fine-grained control when needed.
**Example** — Using the builder to combine multiple source types with configuration:
```csharp
var provider = new AgentSkillsProviderBuilder()
.UseFileSkill("./skills") // file-based source
.UseInlineSkills(codeSkill) // code-defined source
.UseClassSkills(new ClassSkill()) // class-based source
.UseFileScriptRunner(SubprocessScriptRunner.RunAsync) // script runner
.UseScriptApproval() // optional human-in-the-loop
.UsePromptTemplate(customTemplate) // optional prompt customization
.UseFilter(s => s.Frontmatter.Name != "internal") // optional skill filtering
.Build();
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
AIContextProviders = [provider],
});
```
## Adding a Custom Skill Type
The skills framework is designed for extensibility. While file-based and inline skills cover common
scenarios, you can introduce entirely new skill types by subclassing the four base classes:
| Base class | Purpose |
|-----------------------|-----------------------------------------------------|
| `AgentSkillsSource` | Discovers and loads skills from a particular origin |
| `AgentSkill` | Holds metadata, content, resources, and scripts |
| `AgentSkillResource` | Provides supplementary content to a skill |
| `AgentSkillScript` | Represents an executable action within a skill |
The example below implements a **cloud-based skill type** where skills, resources, and scripts are
all stored in and executed through a remote cloud service (e.g., Azure Blob Storage + Azure Functions).
### Step 1 — Define a custom resource
A `CloudSkillResource` reads resource content from a cloud storage endpoint instead of the local
filesystem:
```csharp
/// <summary>
/// A skill resource backed by a cloud storage endpoint.
/// </summary>
public sealed class CloudSkillResource : AgentSkillResource
{
private readonly HttpClient _httpClient;
public CloudSkillResource(string name, Uri blobUri, HttpClient httpClient, string? description = null)
: base(name, description)
{
BlobUri = blobUri ?? throw new ArgumentNullException(nameof(blobUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <summary>
/// Gets the URI of the cloud blob that holds this resource's content.
/// </summary>
public Uri BlobUri { get; }
/// <inheritdoc/>
public override async Task<object?> ReadAsync(
IServiceProvider? serviceProvider = null,
CancellationToken cancellationToken = default)
{
return await _httpClient.GetStringAsync(BlobUri, cancellationToken).ConfigureAwait(false);
}
}
```
### Step 2 — Define a custom script
A `CloudSkillScript` executes a script by calling a cloud function endpoint, passing arguments as
the request body:
```csharp
/// <summary>
/// A skill script executed via a cloud function endpoint.
/// </summary>
public sealed class CloudSkillScript : AgentSkillScript
{
private readonly HttpClient _httpClient;
public CloudSkillScript(string name, Uri functionUri, HttpClient httpClient, string? description = null)
: base(name, description)
{
FunctionUri = functionUri ?? throw new ArgumentNullException(nameof(functionUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <summary>
/// Gets the URI of the cloud function that runs this script.
/// </summary>
public Uri FunctionUri { get; }
/// <inheritdoc/>
public override async Task<object?> RunAsync(
AgentSkill skill,
AIFunctionArguments arguments,
CancellationToken cancellationToken = default)
{
var json = JsonSerializer.Serialize(arguments);
using var content = new StringContent(json, Encoding.UTF8, "application/json");
var response = await _httpClient.PostAsync(FunctionUri, content, cancellationToken)
.ConfigureAwait(false);
response.EnsureSuccessStatusCode();
return await response.Content.ReadAsStringAsync(cancellationToken).ConfigureAwait(false);
}
}
```
### Step 3 — Define a custom skill
A `CloudSkill` bundles cloud-specific metadata (e.g., the base endpoint) with the standard skill
shape:
```csharp
/// <summary>
/// An <see cref="AgentSkill"/> whose content, resources, and scripts are stored in a cloud service.
/// </summary>
public sealed class CloudSkill : AgentSkill
{
public CloudSkill(
AgentSkillFrontmatter frontmatter,
string content,
Uri endpoint,
IReadOnlyList<AgentSkillResource>? resources = null,
IReadOnlyList<AgentSkillScript>? scripts = null)
{
Frontmatter = frontmatter ?? throw new ArgumentNullException(nameof(frontmatter));
Content = content ?? throw new ArgumentNullException(nameof(content));
Endpoint = endpoint ?? throw new ArgumentNullException(nameof(endpoint));
Resources = resources;
Scripts = scripts;
}
/// <inheritdoc/>
public override AgentSkillFrontmatter Frontmatter { get; }
/// <inheritdoc/>
public override string Content { get; }
/// <summary>
/// Gets the base cloud endpoint for this skill.
/// </summary>
public Uri Endpoint { get; }
/// <inheritdoc/>
public override IReadOnlyList<AgentSkillResource>? Resources { get; }
/// <inheritdoc/>
public override IReadOnlyList<AgentSkillScript>? Scripts { get; }
}
```
### Step 4 — Define a custom source
A `CloudSkillsSource` discovers skills from a cloud catalog API and constructs `CloudSkill`
instances with their associated resources and scripts:
```csharp
/// <summary>
/// A skill source that discovers and loads skills from a cloud catalog API.
/// </summary>
public sealed class CloudSkillsSource : AgentSkillsSource
{
private readonly Uri _catalogUri;
private readonly HttpClient _httpClient;
public CloudSkillsSource(Uri catalogUri, HttpClient httpClient)
{
_catalogUri = catalogUri ?? throw new ArgumentNullException(nameof(catalogUri));
_httpClient = httpClient ?? throw new ArgumentNullException(nameof(httpClient));
}
/// <inheritdoc/>
public override async Task<IList<AgentSkill>> GetSkillsAsync(
CancellationToken cancellationToken = default)
{
// Fetch the skill catalog from the cloud service.
var json = await _httpClient.GetStringAsync(_catalogUri, cancellationToken)
.ConfigureAwait(false);
var catalog = JsonSerializer.Deserialize<CloudSkillCatalog>(json)!;
var skills = new List<AgentSkill>();
foreach (var entry in catalog.Skills)
{
var frontmatter = new AgentSkillFrontmatter(entry.Name, entry.Description);
// Build cloud-backed resources.
var resources = entry.Resources
.Select(r => new CloudSkillResource(r.Name, r.BlobUri, _httpClient, r.Description))
.ToList<AgentSkillResource>();
// Build cloud-backed scripts.
var scripts = entry.Scripts
.Select(s => new CloudSkillScript(s.Name, s.FunctionUri, _httpClient, s.Description))
.ToList<AgentSkillScript>();
skills.Add(new CloudSkill(frontmatter, entry.Content, entry.Endpoint, resources, scripts));
}
return skills;
}
}
```
### Step 5 — Register with the builder
Use `UseSource` to wire the custom source into the provider:
```csharp
var httpClient = new HttpClient();
var provider = new AgentSkillsProviderBuilder()
.UseSource(new CloudSkillsSource(
new Uri("https://my-service.example.com/skills/catalog"),
httpClient))
// Mix with other source types if needed:
.UseFileSkill("/local/skills", scriptRunner)
.UseInlineSkills(someInlineSkill)
.Build();
```
The `AgentSkillsProvider` handles all skill types uniformly — any combination of file-based, inline,
class-based, and custom skills can coexist in the same provider. Custom skills automatically
participate in the model-facing tools (`load_skill`, `read_skill_resource`, `run_skill_script`),
filtering, deduplication, and caching — no additional integration work is required.
## Script Representation: `AgentSkillScript` vs `AIFunction`
Two approaches were considered for representing executable scripts within skills:
### Option A — Custom `AgentSkillScript` abstract base class (original design)
Scripts are modeled as a custom `AgentSkillScript` abstract class with `Name`, `Description`, and
`RunAsync(AgentSkill, AIFunctionArguments, CancellationToken)`. Concrete implementations:
`AgentInlineSkillScript` (wraps a delegate/`AIFunction`) and `AgentFileSkillScript` (wraps a file path + executor delegate).
```csharp
// Base type
public abstract class AgentSkillScript
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> RunAsync(AgentSkill skill, AIFunctionArguments arguments, CancellationToken cancellationToken = default);
}
// AgentSkill exposes scripts as:
public abstract IReadOnlyList<AgentSkillScript>? Scripts { get; }
// Inline script wraps an AIFunction internally
var script = new AgentInlineSkillScript(ConvertUnits, "convert");
// Pre-built AIFunction must be wrapped
var script = new AgentInlineSkillScript(myAIFunction);
// Class-based skill declares scripts as:
public override IReadOnlyList<AgentSkillScript>? Scripts { get; } =
[
new AgentInlineSkillScript(ConvertUnits, "convert"),
];
// Provider executes scripts by passing the owning skill:
await script.RunAsync(skill, arguments, cancellationToken);
```
**Pros:**
- **Explicit skill context at execution time.** `RunAsync` receives the owning `AgentSkill`, so any script can access skill metadata or resources during execution without requiring construction-time wiring.
- **Self-contained abstraction.** A dedicated type communicates clearly that scripts are a skills-framework concept, separate from general-purpose AI functions.
- **Easier extensibility for custom script types.** Third-party implementations can subclass `AgentSkillScript` and access the owning skill in `RunAsync` without special setup.
**Cons:**
- **Wrapper overhead.** `AgentInlineSkillScript` is a thin pass-through around `AIFunction` — it adds a class, a constructor, and an indirection layer for no behavioral difference.
- **Parallel abstraction.** `AgentSkillScript` and `AIFunction` serve overlapping purposes (named callable with arguments), creating two parallel hierarchies for the same concept.
- **Friction for consumers.** Users who already have `AIFunction` instances must wrap them in `AgentInlineSkillScript` to use them as scripts, adding ceremony.
### Option B — Reuse `AIFunction` directly
Scripts are represented as `AIFunction` (from `Microsoft.Extensions.AI`). `AgentSkill.Scripts` returns
`IReadOnlyList<AIFunction>?`. `AgentInlineSkillScript` is eliminated entirely — callers use
`AIFunctionFactory.Create(delegate, name: ...)` or pass `AIFunction` instances directly.
`AgentFileSkillScript` becomes an `AIFunction` subclass that captures its owning `AgentFileSkill` via
an internal back-reference set during construction.
```csharp
// AgentSkill exposes scripts as AIFunction directly:
public abstract IReadOnlyList<AIFunction>? Scripts { get; }
// Inline scripts use AIFunctionFactory — no wrapper class needed
var skill = new AgentInlineSkill("my-skill", "desc", "instructions");
skill.AddScript(ConvertUnits, "convert"); // delegate
skill.AddScript(myAIFunction); // pre-built AIFunction — no wrapping
// Class-based skill declares scripts as:
public override IReadOnlyList<AIFunction>? Scripts { get; } =
[
AIFunctionFactory.Create(ConvertUnits, name: "convert"),
];
// Provider executes scripts via standard AIFunction invocation:
await script.InvokeAsync(arguments, cancellationToken);
// File-based scripts extend AIFunction and capture the owning skill internally:
public sealed class AgentFileSkillScript : AIFunction
{
internal AgentFileSkill? Skill { get; set; } // set by AgentFileSkill constructor
protected override async ValueTask<object?> InvokeCoreAsync(
AIFunctionArguments arguments, CancellationToken cancellationToken)
{
return await _executor(Skill!, this, arguments, cancellationToken);
}
}
```
**Pros:**
- **Fewer types.** Eliminates `AgentSkillScript` and `AgentInlineSkillScript`, reducing the public API surface by two classes.
- **Seamless interop.** Any `AIFunction` — whether from `AIFunctionFactory`, a custom subclass, or an external library — can be used as a skill script with zero wrapping.
- **Consistent with `Microsoft.Extensions.AI` ecosystem.** Scripts share the same type as tool functions used by `IChatClient` and `FunctionInvokingChatClient`, reducing conceptual overhead for developers already familiar with the ecosystem.
**Cons:**
- **No owning-skill context in invocation signature.** `AIFunction.InvokeAsync` does not accept an `AgentSkill` parameter, so `AgentFileSkillScript` must capture its owning skill via an internal setter during construction. This adds a construction-order dependency: the skill must set the back-reference on its scripts.
- **Custom script types lose automatic skill access.** Third-party `AIFunction` subclasses that need the owning skill must implement their own mechanism (e.g., constructor injection, closure capture) instead of receiving it as a method parameter.
- **Semantic overloading.** `AIFunction` now means both "a tool the model can call" and "a script within a skill", which could blur the distinction for framework users.
## Resource Representation: `AgentSkillResource` vs `AIFunction`
Two approaches were considered for representing skill resources (supplementary content such as references, assets, or dynamic data):
### Option A — Custom `AgentSkillResource` abstract base class (original design)
Resources are modeled as a custom `AgentSkillResource` abstract class with `Name`, `Description`, and
`ReadAsync(IServiceProvider?, CancellationToken)`. Concrete implementations:
`AgentInlineSkillResource` (static value, delegate, or `AIFunction` wrapper) and `AgentFileSkillResource` (reads file content from disk).
```csharp
// Base type
public abstract class AgentSkillResource
{
public string Name { get; }
public string? Description { get; }
public abstract Task<object?> ReadAsync(IServiceProvider? serviceProvider = null, CancellationToken cancellationToken = default);
}
// AgentSkill exposes resources as:
public abstract IReadOnlyList<AgentSkillResource>? Resources { get; }
// Static resource
var resource = new AgentInlineSkillResource("static content", "my-resource");
// Dynamic resource (delegate)
var resource = new AgentInlineSkillResource((IServiceProvider sp) => GetData(sp), "my-resource");
// Pre-built AIFunction must be wrapped
var resource = new AgentInlineSkillResource(myAIFunction);
// Class-based skill declares resources as:
public override IReadOnlyList<AgentSkillResource>? Resources { get; } =
[
new AgentInlineSkillResource("# Conversion Tables\n...", "conversion-table"),
];
// Provider reads resources via:
await resource.ReadAsync(serviceProvider, cancellationToken);
```
**Pros:**
- **Clear semantic distinction.** A dedicated `AgentSkillResource` type distinguishes resources (data providers) from scripts (executable actions), making the API self-documenting.
- **Purpose-built API.** `ReadAsync` communicates intent better than `InvokeAsync` for a data-access operation.
**Cons:**
- **Wrapper overhead.** `AgentInlineSkillResource` wraps `AIFunction` internally for delegate/function cases — adding a class and indirection for no behavioral difference.
- **Parallel abstraction.** `AgentSkillResource` and `AIFunction` serve overlapping purposes (named callable that returns data), creating two parallel hierarchies.
- **Friction for consumers.** Users who already have `AIFunction` instances must wrap them in `AgentInlineSkillResource`, adding ceremony.
### Option B — Reuse `AIFunction` directly
Resources are represented as `AIFunction`. `AgentSkill.Resources` returns `IReadOnlyList<AIFunction>?`.
`AgentInlineSkillResource` becomes an `AIFunction` subclass (retained as a convenience for the static-value
pattern: `new AgentInlineSkillResource("data", "name")`). `AgentFileSkillResource` becomes an `AIFunction`
subclass that reads file content.
```csharp
// AgentSkill exposes resources as AIFunction directly:
public abstract IReadOnlyList<AIFunction>? Resources { get; }
// Static resource — AgentInlineSkillResource is retained as a convenience AIFunction subclass
var resource = new AgentInlineSkillResource("static content", "my-resource");
// Dynamic resource — AgentInlineSkillResource wraps delegate as AIFunction
var resource = new AgentInlineSkillResource((IServiceProvider sp) => GetData(sp), "my-resource");
// Pre-built AIFunction can be used directly — no wrapping needed
skill.AddResource(myAIFunction);
// Class-based skill declares resources as:
public override IReadOnlyList<AIFunction>? Resources { get; } =
[
new AgentInlineSkillResource("# Conversion Tables\n...", "conversion-table"),
];
// Provider reads resources via standard AIFunction invocation:
await resource.InvokeAsync(arguments, cancellationToken);
// File-based resources extend AIFunction directly:
internal sealed class AgentFileSkillResource : AIFunction
{
public string FullPath { get; }
protected override async ValueTask<object?> InvokeCoreAsync(
AIFunctionArguments arguments, CancellationToken cancellationToken)
{
return await File.ReadAllTextAsync(FullPath, Encoding.UTF8, cancellationToken);
}
}
```
**Pros:**
- **Fewer base types.** Eliminates the `AgentSkillResource` abstract class, reducing the public API surface.
- **Seamless interop.** Any `AIFunction` can be used as a skill resource with zero wrapping.
**Cons:**
- **Loss of semantic distinction.** Resources and scripts are now both `AIFunction`, which could make it less obvious which list a function belongs to when reading code.
- **Static values require a wrapper.** Unlike the original `ReadAsync` which could return a stored value directly, `AIFunction.InvokeAsync` implies invocation. `AgentInlineSkillResource` is retained as a convenience subclass to handle the static-value case, so this is not eliminated — just moved to a different class.
## Decision Outcome
### 1. Keep `AgentSkillResource` and `AgentSkillScript` (Option A for both sections)
We are staying with the custom `AgentSkillResource` and `AgentSkillScript` model classes instead of reusing `AIFunction`:
- **Resources have no parameters.** If a consumer provides an `AIFunction` with parameters, those parameters will never be advertised to the LLM, and the resulting call will fail.
- **Approval breaks for `AIFunction`-based representations.** When a resource or script represented by an `AIFunction` is configured with approval, the second approval invocation will not work correctly.
- **Injecting the owning skill into an `AIFunction`-based script is problematic.** Constructor injection would introduce a circular reference between the skill and the script. An internal property setter is possible but adds coupling.
### 2. Make all agent skill classes internal
All agent-skill-related classes are made `internal` to minimize the public API surface while the feature matures. We can reconsider and promote types to `public` later based on community signal.
This leaves two public entry points:
- **`AgentSkillsProvider`** — use directly when all skills come from a single source and filtering is not needed.
- **`AgentSkillsProviderBuilder`** — use when mixing skill types or when filtering support is required.
### 3. Caching at provider level
Caching of tools and instructions is implemented inside `AgentSkillsProvider` rather than as an external decorator. Recreating tools and instructions on every provider call is wasteful, and a caching decorator sitting outside the provider would not have the information needed to cache them effectively.
@@ -1,72 +0,0 @@
---
status: accepted
contact: eavanvalkenburg
date: 2026-03-20
deciders: eavanvalkenburg, sphenry, chetantoshnival
consulted: taochenosu, moonbox3, dmytrostruk, giles17, alliscode
---
# Provider-Leading Client Design & OpenAI Package Extraction
## Context and Problem Statement
The `agent-framework-core` package currently bundles OpenAI and Azure OpenAI client implementations along with their dependencies (`openai`, `azure-identity`, `azure-ai-projects`, `packaging`). This makes core heavier than necessary for users who don't use OpenAI, and it conflates the core abstractions with a specific provider implementation. Additionally, the current class naming (`OpenAIResponsesClient`, `OpenAIChatClient`) is based on the underlying OpenAI API names rather than what users actually want to do, making discoverability harder for newcomers.
## Decision Drivers
- **Lightweight core**: Core should only contain abstractions, middleware infrastructure, and telemetry — no provider-specific code or dependencies.
- **Discoverability-first**: Import namespaces should guide users to the right client. `from agent_framework.openai import ...` should surface all OpenAI-related clients; `from agent_framework.azure import ...` should surface Foundry, Azure AI, and other Azure-specific classes.
- **Provider-leading naming**: The primary client name should reflect the provider, not the underlying API. The Responses API is now the recommended default for OpenAI, so its client should be called `OpenAIChatClient` (not `OpenAIResponsesClient`).
- **Clean separation of concerns**: Azure-specific deprecated wrappers belong in the azure-ai package, not in the OpenAI package.
## Considered Options
- **Keep OpenAI in core**: Simpler but keeps core heavy; doesn't help discoverability.
- **Extract OpenAI with Azure wrappers in the OpenAI package**: Keeps Azure OpenAI wrappers alongside OpenAI code, but pollutes the OpenAI package with Azure concerns.
- **Extract OpenAI, place Azure wrappers in azure-ai**: Clean separation; the OpenAI package has zero Azure dependencies; deprecated Azure wrappers live in a single file in azure-ai for easy future deletion.
## Decision Outcome
Chosen option: "Extract OpenAI, place Azure wrappers in azure-ai", because it achieves the lightest core, cleanest OpenAI package, and the most maintainable deprecation path.
Key changes:
1. **New `agent-framework-openai` package** with dependencies on `agent-framework-core`, `openai`, and `packaging` only.
2. **Class renames**: `OpenAIResponsesClient``OpenAIChatClient` (Responses API), `OpenAIChatClient``OpenAIChatCompletionClient` (Chat Completions API). Old names remain as deprecated aliases.
3. **Deprecated classes**: `OpenAIAssistantsClient`, all `AzureOpenAI*Client` classes, `AzureAIClient`, `AzureAIAgentClient`, and `AzureAIProjectAgentProvider` are marked deprecated.
4. **New `FoundryChatClient`** in azure-ai for Azure AI Foundry Responses API access, built on `RawFoundryChatClient(RawOpenAIChatClient)`.
5. **All deprecated `AzureOpenAI*` classes** consolidated into a single file (`_deprecated_azure_openai.py`) in the azure-ai package for clean future deletion.
6. **Core's `agent_framework.openai` and `agent_framework.azure` namespaces** become lazy-loading gateways, preserving backward-compatible import paths while removing hard dependencies.
7. **Unified `model` parameter** replaces `model_id` (OpenAI), `deployment_name` (Azure OpenAI), and `model_deployment_name` (Azure AI) across all client constructors. The term `model` is intentionally generic: it naturally maps to an OpenAI model name *and* to an Azure OpenAI deployment name, making it straightforward to use `OpenAIChatClient` with either OpenAI or Azure OpenAI backends (via `AsyncAzureOpenAI`). Environment variables are similarly unified (e.g., `OPENAI_MODEL` instead of separate `OPENAI_RESPONSES_MODEL_ID` / `OPENAI_CHAT_MODEL_ID`).
8. **`FoundryAgent`** replaces the pattern of `Agent(client=AzureAIClient(...))` for connecting to pre-configured agents in Azure AI Foundry (PromptAgents and HostedAgents). The underlying `RawFoundryAgentChatClient` is an implementation detail — most users interact only with `FoundryAgent`. `AzureAIAgentClient` is separately deprecated as it refers to the V1 Agents Service API. See below for design rationale.
### Foundry Agent Design: `FoundryAgentClient` vs `FoundryAgent`
The existing `AzureAIClient` combines two concerns: CRUD lifecycle management (creating/deleting agents on the service) and runtime communication (sending messages via the Responses API). The new design removes CRUD entirely — users connect to agents that already exist in Foundry.
**Two approaches were considered:**
**Option A — `FoundryAgentClient` only (public ChatClient):**
Users compose `Agent(client=FoundryAgentClient(...), tools=[...])`. This follows the universal `Agent(client=X)` pattern used by every other provider. However, a "client" that wraps a named remote agent (with `agent_name` as a constructor param) is semantically odd — clients typically wrap a model endpoint, not a specific agent.
**Option B — `FoundryAgent` (Agent subclass) + private `_FoundryAgentChatClient` and public `RawFoundryAgentChatClient`:**
Users write `FoundryAgent(agent_name="my-agent", ...)` for the common case. Internally, `FoundryAgent` creates a `_FoundryAgentChatClient` and passes it to the standard `Agent` base class. For advanced customization, users pass `client_type=RawFoundryAgentChatClient` (or a custom subclass) to control the client middleware layers. The `Agent(client=RawFoundryAgentChatClient(...))` composition pattern still works for users who prefer it.
**Chosen option: Option B**, because:
- The common case (`FoundryAgent(...)`) is a single object with no boilerplate.
- `client_type=` gives full control over client middleware without parameter duplication — the agent forwards connection params to the client internally.
- `RawFoundryAgent(RawAgent)` and `FoundryAgent(Agent)` mirror the established `RawAgent`/`Agent` pattern.
- Runtime validation (only `FunctionTool` allowed) lives in `RawFoundryAgentChatClient._prepare_options`, ensuring it applies regardless of how the client is used — through `FoundryAgent`, `Agent(client=...)`, or any custom composition.
**Public classes:**
- `RawFoundryAgentChatClient(RawOpenAIChatClient)` — Responses API client that injects agent reference and validates tools. Extension point for custom client middleware.
- `RawFoundryAgent(RawAgent)` — Agent without agent-level middleware/telemetry.
- `FoundryAgent(AgentTelemetryLayer, AgentMiddlewareLayer, RawFoundryAgent)` — Recommended production agent.
**Internal (private):**
- `_FoundryAgentChatClient` — Full client with function invocation, chat middleware, and telemetry layers. Created automatically by `FoundryAgent`; users customize via `client_type=RawFoundryAgentChatClient` or a custom subclass.
**Deprecated:**
- `AzureAIClient` — replaced by `FoundryAgent` (which uses `FoundryAgentClient` internally).
- `AzureAIAgentClient` — refers to V1 Agents Service API, no direct replacement.
- `AzureAIProjectAgentProvider` — replaced by `FoundryAgent`.
@@ -1,116 +0,0 @@
---
status: accepted
contact: westey-m
date: 2026-03-23
deciders: sergeymenshykh, markwallace, rbarreto, dmytrostruk, westey-m, eavanvalkenburg, stephentoub
consulted:
informed:
---
# Chat History Persistence Consistency
## Context and Problem Statement
When using `ChatClientAgent` with tools, the `FunctionInvokingChatClient` (FIC) loops multiple times — service call → tool execution → service call → … — before producing a final response. There are two points of discrepancy between how chat history is stored by the framework's `ChatHistoryProvider` and how the underlying AI service stores chat history (e.g., OpenAI Responses with `store=true`):
1. **Persistence timing**: The AI service persists messages after *each* service call within the FIC loop. The `ChatHistoryProvider` currently persists messages only once, at the *end* of the full agent run (after all FIC loop iterations complete).
2. **Trailing `FunctionResultContent` storage**: When tool calling is terminated mid-loop (e.g., via `FunctionInvokingChatClient` termination filters), the final response from the agent may contain `FunctionResultContent` that was never sent to a subsequent service call. The AI service never stores this trailing `FunctionResultContent`, but the `ChatHistoryProvider` currently stores all response content, including the trailing `FunctionResultContent`.
These discrepancies mean that a `ChatHistoryProvider`-managed conversation and a service-managed conversation can diverge in content and structure, even when processing the same interactions.
### Practical Impact: Resuming After Tool-Call Termination
Today, users of `AIAgent` get different behaviors depending on whether chat history is stored service-side or in a `ChatHistoryProvider`. This creates concrete challenges — for example, when the function call loop is terminated and the user wants to resume the conversation in a subsequent run. With service-stored history, the trailing `FunctionResultContent` is never persisted, so the last stored message is the `FunctionCallContent` from the service. With `ChatHistoryProvider`-stored history, the trailing `FunctionResultContent` *is* persisted. The user cannot know whether the last `FunctionResultContent` is in the chat history or not without inspecting the storage mechanism, making it difficult to write resumption logic that works correctly regardless of the storage backend.
### Relationship Between the Two Discrepancies
The persistence timing and `FunctionResultContent` trimming behaviors are interrelated:
- **Per-service-call persistence**: When messages are persisted after each individual service call, trailing `FunctionResultContent` trimming is unnecessary. If tool calling is terminated, the `FunctionResultContent` from the terminated call was never sent to a subsequent service call, so it is never persisted. The per-service-call approach naturally matches the service's behavior.
- **Per-run persistence**: When messages are batched and persisted at the end of the full run, trailing `FunctionResultContent` trimming becomes necessary to match the service's behavior. Without trimming, the stored history contains `FunctionResultContent` that the service would never have stored.
This means the trimming feature (introduced in [PR #4792](https://github.com/microsoft/agent-framework/pull/4792)) is primarily needed as a complement to per-run persistence. The `PersistChatHistoryAtEndOfRun` setting (introduced in [PR #4762](https://github.com/microsoft/agent-framework/pull/4762)) inverts the default so that per-service-call persistence is the standard behavior, and per-run persistence is opt-in.
## Decision Drivers
- **A. Consistency**: The default behavior of `ChatHistoryProvider` should produce stored history that closely matches what the underlying AI service would store, minimizing surprise when switching between framework-managed and service-managed chat history.
- **B. Atomicity**: A run that fails mid-way through a multi-step tool-calling loop should not leave chat history in a partially-updated state, unless the user explicitly opts into that behavior.
- **C. Recoverability**: For long-running tool-calling loops, it should be possible to recover intermediate progress if the process is interrupted, rather than losing all work from the current run.
- **D. Simplicity**: The default behavior should be easy to understand and predict for most users, without requiring knowledge of the FIC loop internals.
- **E. Flexibility**: Regardless of the chosen default, users should be able to opt into the alternative behavior.
## Considered Options
- Option 1: Default to per-run persistence with `FunctionResultContent` trimming (opt-in to per-service-call)
- Option 2: Default to per-service-call persistence (opt-in to per-run)
## Pros and Cons of the Options
### Option 1: Default to per-run persistence with `FunctionResultContent` trimming
Keep the current default behavior of persisting chat history only at the end of the full agent run. Add `FunctionResultContent` trimming as the default to improve consistency with service storage. Provide an opt-in setting for users who want per-service-call persistence.
Settings:
- `PersistChatHistoryAtEndOfRun` = `true`
- Good, because runs are atomic — chat history is only updated when the full run succeeds, satisfying driver B.
- Good, because the mental model is simple: one run = one history update, satisfying driver D.
- Good, because trimming trailing `FunctionResultContent` improves consistency with service storage, partially satisfying driver A.
- Good, because users can opt in to per-service-call persistence for checkpointing/recovery scenarios, satisfying drivers C and E.
- Bad, because the default persistence timing still differs from the service's behavior (per-run vs. per-service-call), only partially satisfying driver A.
- Bad, because if the process crashes mid-loop, all intermediate progress from the current run is lost, not satisfying driver C by default.
### Option 2: Default to per-service-call persistence
Change the default to persist chat history after each individual service call within the FIC loop, matching the AI service's behavior. Trailing `FunctionResultContent` trimming is unnecessary with this approach (it is naturally handled). Provide an opt-in setting for users who want per-run atomicity with trimming.
Settings:
- `PersistChatHistoryAtEndOfRun` = `false` (default)
- Good, because the stored history matches the service's behavior by default for both timing and content, fully satisfying driver A.
- Good, because intermediate progress is preserved if the process is interrupted, satisfying driver C.
- Good, because no separate `FunctionResultContent` trimming logic is needed, reducing complexity.
- Bad, because chat history may be left in an incomplete state if the run fails mid-loop (e.g., `FunctionCallContent` stored without corresponding `FunctionResultContent`), not satisfying driver B. A subsequent run cannot proceed without manually providing the missing `FunctionResultContent`.
- Bad, because the mental model is more complex: a single run may produce multiple history updates, partially failing driver D.
- Neutral, because users can opt out to per-run persistence if they prefer atomicity, satisfying driver E.
## Decision Outcome
Chosen option: **Option 2 — Default to per-service-call persistence**, because it fully satisfies the consistency driver (A), naturally handles `FunctionResultContent` trimming without additional logic, and provides better recoverability for long-running tool-calling loops. Per-run persistence remains available via the `PersistChatHistoryAtEndOfRun` setting for users who prefer atomic run semantics.
### Configuration Matrix
The behavior depends on the combination of `UseProvidedChatClientAsIs` and `PersistChatHistoryAtEndOfRun`:
| `UseProvidedChatClientAsIs` | `PersistChatHistoryAtEndOfRun` | Behavior |
|---|---|---|
| `false` (default) | `false` (default) | **Per-service-call persistence.** A `ChatHistoryPersistingChatClient` middleware is automatically injected into the chat client pipeline between `FunctionInvokingChatClient` and the leaf `IChatClient`. Messages are persisted after each service call. |
| `true` | `false` | **User responsibility.** No middleware is injected because the user has provided a custom chat client stack. The user is responsible for ensuring correct persistence behavior (e.g., by including their own persisting middleware). |
| `false` | `true` | **Per-run persistence with marking.** A `ChatHistoryPersistingChatClient` middleware is injected, but configured to *mark* messages with metadata rather than store them immediately. At the end of the run, marked messages are stored. Trailing `FunctionResultContent` is trimmed. |
| `true` | `true` | **Per-run persistence with warning.** The system checks whether the custom chat client stack includes a `ChatHistoryPersistingChatClient`. If not, a warning is emitted (particularly relevant for workflow handoff scenarios where trimming cannot be guaranteed). If no `ChatHistoryPersistingChatClient` is preset, all messages are stored at the end of the run, otherwise marked messages are stored. |
### Consequences
- Good, because the stored history matches the service's behavior by default for both timing and content, fully satisfying consistency (driver A).
- Good, because intermediate progress is preserved if the process is interrupted, satisfying recoverability (driver C).
- Good, because no separate `FunctionResultContent` trimming logic is needed in the default path, reducing complexity.
- Good, because marking persisted messages with metadata enables deduplication and aids debugging.
- Good, because warnings for custom chat client configurations without the persisting middleware help prevent silent failures in workflow handoff scenarios.
- Bad, because chat history may be left in an incomplete state if the run fails mid-loop (e.g., `FunctionCallContent` stored without corresponding `FunctionResultContent`), requiring manual recovery in rare cases.
- Bad, because the mental model is more complex for the default path: a single run may produce multiple history updates.
- Neutral, because users who prefer atomic run semantics can opt in to per-run persistence via `PersistChatHistoryAtEndOfRun = true`.
- Neutral, because increased write frequency from per-service-call persistence may impact performance for some storage backends; this can be mitigated with a caching decorator.
### Implementation Notes
#### Conversation ID Consistency
The `ChatHistoryPersistingChatClient` middleware must also update the session's `ConversationId` consistently for both response-based and conversation-based service interactions, ensuring the session always reflects the latest service-provided identifier.
## More Information
- [PR #4762: Persist messages during function call loop](https://github.com/microsoft/agent-framework/pull/4762) — introduces `PersistChatHistoryAfterEachServiceCall` option and `ChatHistoryPersistingChatClient` decorator
- [PR #4792: Trim final FRC to match service storage](https://github.com/microsoft/agent-framework/pull/4792) — introduces `StoreFinalFunctionResultContent` option and `FilterFinalFunctionResultContent` logic
- [Issue #2889](https://github.com/microsoft/agent-framework/issues/2889) — original issue tracking chat history persistence during function call loops
+5 -50
View File
@@ -17,17 +17,14 @@ dotnet format # Auto-fix formatting for all projects
# Build/test/format a specific project (preferred for isolated/internal changes)
dotnet build src/Microsoft.Agents.AI.<Package> --tl:off
dotnet test --project tests/Microsoft.Agents.AI.<Package>.UnitTests
dotnet test tests/Microsoft.Agents.AI.<Package>.UnitTests
dotnet format src/Microsoft.Agents.AI.<Package>
# Run a single test
# Replace the filter values with the appropriate assembly, namespace, class, and method names for the test you want to run and use * as a wildcard elsewhere, e.g. "/*/*/HttpClientTests/GetAsync_ReturnsSuccessStatusCode"
# Use `--ignore-exit-code 8` to avoid failing the build when no tests are found for some projects
dotnet test --filter-query "/<assemblyFilter>/<namespaceFilter>/<classFilter>/<methodFilter>" --ignore-exit-code 8
dotnet test --filter "FullyQualifiedName~Namespace.TestClassName.TestMethodName"
# Run unit tests only
# Use `--ignore-exit-code 8` to avoid failing the build when no tests are found for integration test projects
dotnet test --filter-query "/*UnitTests*/*/*/*" --ignore-exit-code 8
dotnet test --filter FullyQualifiedName\~UnitTests
```
Use `--tl:off` when building to avoid flickering when running commands in the agent.
@@ -59,7 +56,7 @@ Example: Running tests for a single project using .NET 10.
```bash
# From dotnet/ directory
dotnet test --project ./tests/Microsoft.Agents.AI.Abstractions.UnitTests -f net10.0
dotnet test ./tests/Microsoft.Agents.AI.Abstractions.UnitTests -f net10.0
```
Example: Running a single test in a specific project using .NET 10.
@@ -67,7 +64,7 @@ Provide the full namespace, class name, and method name for the test you want to
```bash
# From dotnet/ directory
dotnet test --project ./tests/Microsoft.Agents.AI.Abstractions.UnitTests -f net10.0 --filter-query "/*/Microsoft.Agents.AI.Abstractions.UnitTests/AgentRunOptionsTests/CloningConstructorCopiesProperties"
dotnet test ./tests/Microsoft.Agents.AI.Abstractions.UnitTests -f net10.0 --filter "FullyQualifiedName~Microsoft.Agents.AI.Abstractions.UnitTests.AgentRunOptionsTests.CloningConstructorCopiesProperties"
```
### Multi-target framework tip
@@ -86,45 +83,3 @@ Just remember to run `dotnet restore` after pulling changes, making changes to p
Unit tests target both .NET Framework as well as .NET Core. When running on Linux, only the .NET Core tests can be run, as .NET Framework is not supported on Linux.
To run only the .NET Core tests, use the `-f net10.0` option with `dotnet test`.
### Microsoft Testing Platform (MTP)
Tests use the [Microsoft Testing Platform](https://learn.microsoft.com/dotnet/core/testing/unit-testing-platform-intro) via xUnit v3. Key differences from the legacy VSTest runner:
- **`dotnet test` requires `--project`** to specify a test project directly (positional arguments are no longer supported).
- **Test output** uses the MTP format (e.g., `[✓112/x0/↓0]` progress and `Test run summary: Passed!`).
- **TRX reports** use `--report-xunit-trx` instead of `--logger trx`.
- **Code coverage** uses `Microsoft.Testing.Extensions.CodeCoverage` with `--coverage --coverage-output-format cobertura`.
- **Running a test project directly** is supported via `dotnet run --project <test-project>`. This bypasses the `dotnet test` infrastructure and runs the test executable directly with the MTP command line.
- **Running tests across the solution** with a filter may cause some projects to match zero tests, which MTP treats as a failure (exit code 8). Use `--ignore-exit-code 8` to suppress this:
```bash
# Run all unit tests across the solution, ignoring projects with no matching tests
dotnet test --solution ./agent-framework-dotnet.slnx --no-build -f net10.0 --ignore-exit-code 8
```
- **Running tests with `--solution` for a specific TFM** requires all projects in the solution to support that TFM. Not all projects target every framework (e.g., some are `net10.0`-only). Use `./dotnet/eng/scripts/New-FilteredSolution.ps1` to generate a filtered solution:
```powershell
# Generate a filtered solution for net472 and run tests
$filtered = ./dotnet/eng/scripts/New-FilteredSolution.ps1 -Solution dotnet/agent-framework-dotnet.slnx -TargetFramework net472
dotnet test --solution $filtered --no-build -f net472 --ignore-exit-code 8
# Exclude samples and keep only unit test projects
./dotnet/eng/scripts/New-FilteredSolution.ps1 -Solution dotnet/agent-framework-dotnet.slnx -TargetFramework net10.0 -ExcludeSamples -TestProjectNameFilter "*UnitTests*" -OutputPath dotnet/filtered-unit.slnx
```
```bash
# Run tests via dotnet test (uses MTP under the hood)
dotnet test --project ./tests/Microsoft.Agents.AI.UnitTests -f net10.0
# Run tests with code coverage (Cobertura format)
dotnet test --project ./tests/Microsoft.Agents.AI.UnitTests -f net10.0 --coverage --coverage-output-format cobertura --coverage-settings ./tests/coverage.runsettings
# Run tests directly via dotnet run (MTP native command line)
dotnet run --project ./tests/Microsoft.Agents.AI.UnitTests -f net10.0
# Show MTP command line help
dotnet run --project ./tests/Microsoft.Agents.AI.UnitTests -f net10.0 -- -?
```
+35 -36
View File
@@ -11,18 +11,19 @@
</PropertyGroup>
<ItemGroup>
<!-- Aspire.* -->
<PackageVersion Include="Anthropic" Version="12.8.0" />
<PackageVersion Include="Anthropic.Foundry" Version="0.4.2" />
<PackageVersion Include="Anthropic" Version="12.3.0" />
<PackageVersion Include="Anthropic.Foundry" Version="0.4.1" />
<PackageVersion Include="Aspire.Azure.AI.OpenAI" Version="13.0.0-preview.1.25560.3" />
<PackageVersion Include="Aspire.Hosting.AppHost" Version="$(AspireAppHostSdkVersion)" />
<PackageVersion Include="Aspire.Hosting.Azure.CognitiveServices" Version="$(AspireAppHostSdkVersion)" />
<PackageVersion Include="Aspire.Microsoft.Azure.Cosmos" Version="$(AspireAppHostSdkVersion)" />
<PackageVersion Include="CommunityToolkit.Aspire.OllamaSharp" Version="13.0.0" />
<!-- Azure.* -->
<PackageVersion Include="Azure.AI.Projects" Version="2.0.0-beta.2" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.10" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.9.0-beta.1" />
<PackageVersion Include="Azure.Identity" Version="1.19.0" />
<PackageVersion Include="Azure.AI.Projects" Version="1.2.0-beta.5" />
<PackageVersion Include="Azure.AI.Projects.OpenAI" Version="1.0.0-beta.5" />
<PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.8" />
<PackageVersion Include="Azure.AI.OpenAI" Version="2.8.0-beta.1" />
<PackageVersion Include="Azure.Identity" Version="1.17.1" />
<PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.4.0" />
<!-- Google Gemini -->
<PackageVersion Include="Google.GenAI" Version="0.11.0" />
@@ -32,19 +33,18 @@
<!-- Newtonsoft.Json -->
<PackageVersion Include="Newtonsoft.Json" Version="13.0.4" />
<!-- System.* -->
<PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.4" />
<PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.3" />
<PackageVersion Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
<PackageVersion Include="Microsoft.Bcl.Memory" Version="10.0.4" />
<PackageVersion Include="System.ClientModel" Version="1.9.0" />
<PackageVersion Include="System.ClientModel" Version="1.8.1" />
<PackageVersion Include="System.CodeDom" Version="10.0.0" />
<PackageVersion Include="System.Collections.Immutable" Version="10.0.1" />
<PackageVersion Include="System.CommandLine" Version="2.0.0-rc.2.25502.107" />
<PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.4" />
<PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.4" />
<PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.3" />
<PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.0" />
<PackageVersion Include="System.Net.Http.Json" Version="10.0.0" />
<PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.4" />
<PackageVersion Include="System.Text.Json" Version="10.0.4" />
<PackageVersion Include="System.Threading.Channels" Version="10.0.4" />
<PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.3" />
<PackageVersion Include="System.Text.Json" Version="10.0.3" />
<PackageVersion Include="System.Threading.Channels" Version="10.0.3" />
<PackageVersion Include="System.Threading.Tasks.Extensions" Version="4.6.3" />
<PackageVersion Include="System.Net.Security" Version="4.3.2" />
<!-- OpenTelemetry -->
@@ -63,25 +63,24 @@
<PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.0" />
<PackageVersion Include="Swashbuckle.AspNetCore.SwaggerUI" Version="10.0.0" />
<!-- Microsoft.Extensions.* -->
<PackageVersion Include="Microsoft.Extensions.AI" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Safety" Version="10.3.0-preview.1.26109.11" />
<PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.3.0" />
<PackageVersion Include="Microsoft.Extensions.Caching.Memory" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Compliance.Abstractions" Version="10.4.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.Binder" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.EnvironmentVariables" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.Json" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Configuration.UserSecrets" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.4" />
<PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.3" />
<PackageVersion Include="Microsoft.Extensions.Hosting" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.4" />
<PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.3" />
<PackageVersion Include="Microsoft.Extensions.Logging.Console" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.0.0" />
<PackageVersion Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.7.0" />
@@ -95,25 +94,24 @@
<PackageVersion Include="Microsoft.SemanticKernel.Agents.AzureAI" Version="1.67.0-preview" />
<PackageVersion Include="Microsoft.SemanticKernel.Plugins.OpenApi" Version="1.67.0" />
<!-- Agent SDKs -->
<PackageVersion Include="GitHub.Copilot.SDK" Version="0.1.29" />
<PackageVersion Include="GitHub.Copilot.SDK" Version="0.1.23" />
<PackageVersion Include="Microsoft.Agents.CopilotStudio.Client" Version="1.3.171-beta" />
<!-- M365 Agents SDK -->
<PackageVersion Include="AdaptiveCards" Version="3.1.0" />
<PackageVersion Include="Microsoft.Agents.Authentication.Msal" Version="1.3.171-beta" />
<PackageVersion Include="Microsoft.Agents.Hosting.AspNetCore" Version="1.3.171-beta" />
<!-- A2A -->
<PackageVersion Include="A2A" Version="0.3.4-preview" />
<PackageVersion Include="A2A.AspNetCore" Version="0.3.4-preview" />
<PackageVersion Include="A2A" Version="0.3.3-preview" />
<PackageVersion Include="A2A.AspNetCore" Version="0.3.3-preview" />
<!-- MCP -->
<PackageVersion Include="ModelContextProtocol" Version="1.1.0" />
<PackageVersion Include="ModelContextProtocol" Version="0.8.0-preview.1" />
<!-- Inference SDKs -->
<PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.5.1" />
<PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
<PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />
<PackageVersion Include="OllamaSharp" Version="5.4.8" />
<PackageVersion Include="OpenAI" Version="2.9.1" />
<PackageVersion Include="OpenAI" Version="2.8.0" />
<!-- Identity -->
<PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.83.1" />
<PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.78.0" />
<!-- Workflows -->
<PackageVersion Include="Microsoft.Agents.ObjectModel" Version="2026.2.4.1" />
<PackageVersion Include="Microsoft.Agents.ObjectModel.Json" Version="2026.2.4.1" />
@@ -127,7 +125,7 @@
<!-- Azure Functions -->
<PackageVersion Include="Microsoft.Azure.Functions.Worker" Version="2.50.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.ApplicationInsights" Version="2.50.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" Version="1.12.1" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" Version="1.11.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask.AzureManaged" Version="1.0.1" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http" Version="3.3.0" />
<PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" Version="2.1.0" />
@@ -142,14 +140,15 @@
<PackageVersion Include="Microsoft.AspNetCore.TestHost" Condition="'$(TargetFramework)' == 'net10.0'" Version="10.0.0" />
<PackageVersion Include="Microsoft.NET.Test.Sdk" Version="18.0.0" />
<PackageVersion Include="Moq" Version="[4.18.4]" />
<PackageVersion Include="xunit.v3.mtp-v2" Version="3.2.2" />
<PackageVersion Include="xunit.runner.visualstudio" Version="3.1.5" />
<PackageVersion Include="xRetry.v3" Version="1.0.0-rc3" />
<PackageVersion Include="Microsoft.Testing.Extensions.CodeCoverage" Version="18.4.1" />
<PackageVersion Include="xunit" Version="2.9.3" />
<PackageVersion Include="xunit.abstractions" Version="2.0.3" />
<PackageVersion Include="xunit.runner.visualstudio" Version="3.1.3" />
<PackageVersion Include="Xunit.SkippableFact" Version="1.5.23" />
<PackageVersion Include="xretry" Version="1.9.0" />
<PackageVersion Include="coverlet.collector" Version="6.0.4" />
<!-- Symbols -->
<PackageVersion Include="Microsoft.SourceLink.GitHub" Version="8.0.0" />
<!-- Toolset -->
<PackageVersion Include="ReferenceTrimmer" Version="3.4.5" />
<PackageVersion Include="Microsoft.CodeAnalysis.Analyzers" Version="3.11.0" />
<PackageVersion Include="Microsoft.CodeAnalysis.CSharp" Version="4.14.0" />
<PackageVersion Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100" />
@@ -188,4 +187,4 @@
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
</ItemGroup>
</Project>
</Project>
+36 -72
View File
@@ -1,4 +1,4 @@
<Solution>
<Solution>
<Configurations>
<BuildType Name="Debug" />
<BuildType Name="Publish" />
@@ -56,33 +56,10 @@
<Project Path="samples/02-agents/Agents/Agent_Step15_DeepResearch/Agent_Step15_DeepResearch.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step16_Declarative/Agent_Step16_Declarative.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj" />
<Project Path="samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Agent_Step19_InFunctionLoopCheckpointing.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/DeclarativeAgents/">
<Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
</Folder>
<Folder Name="/Samples/04-hosting/DurableWorkflows/" />
<Folder Name="/Samples/04-hosting/DurableWorkflows/ConsoleApps/">
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/01_SequentialWorkflow/01_SequentialWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/02_ConcurrentWorkflow/02_ConcurrentWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/03_ConditionalEdges/03_ConditionalEdges.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/04_WorkflowAndAgents/04_WorkflowAndAgents.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/05_WorkflowEvents/05_WorkflowEvents.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/06_WorkflowSharedState/06_WorkflowSharedState.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/07_SubWorkflows/07_SubWorkflows.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/ConsoleApps/08_WorkflowHITL/08_WorkflowHITL.csproj" />
</Folder>
<Folder Name="/Samples/04-hosting/DurableWorkflows/AzureFunctions/">
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/01_SequentialWorkflow/01_SequentialWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/02_ConcurrentWorkflow/02_ConcurrentWorkflow.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/03_WorkflowHITL/03_WorkflowHITL.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/04_WorkflowMcpTool/04_WorkflowMcpTool.csproj" />
<Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/05_WorkflowAndAgents/05_WorkflowAndAgents.csproj" />
</Folder>
<Folder Name="/Samples/GettingStarted/">
<File Path="samples/GettingStarted/README.md" />
</Folder>
<Folder Name="/Samples/02-agents/AGUI/">
<File Path="samples/02-agents/AGUI/README.md" />
</Folder>
@@ -104,7 +81,7 @@
</Folder>
<Folder Name="/Samples/02-agents/AgentSkills/">
<File Path="samples/02-agents/AgentSkills/README.md" />
<Project Path="samples/02-agents/AgentSkills/Agent_Step01_FileBasedSkills/Agent_Step01_FileBasedSkills.csproj" />
<Project Path="samples/02-agents/AgentSkills/Agent_Step01_BasicSkills/Agent_Step01_BasicSkills.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AGUI/Step05_StateManagement/">
<Project Path="samples/02-agents/AGUI/Step05_StateManagement/Client/Client.csproj" />
@@ -121,40 +98,11 @@
<Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step03_UsingFunctionTools/Agent_Anthropic_Step03_UsingFunctionTools.csproj" />
<Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step04_UsingSkills/Agent_Anthropic_Step04_UsingSkills.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AgentsWithFoundry/">
<File Path="samples/02-agents/AgentsWithFoundry/README.md" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step00_FoundryAgentLifecycle/Agent_Step00_FoundryAgentLifecycle.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step01_Basics/Agent_Step01_Basics.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step02.1_MultiturnConversation/Agent_Step02.1_MultiturnConversation.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step02.2_MultiturnWithServerConversations/Agent_Step02.2_MultiturnWithServerConversations.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step03_UsingFunctionTools/Agent_Step03_UsingFunctionTools.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step04_UsingFunctionToolsWithApprovals/Agent_Step04_UsingFunctionToolsWithApprovals.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step05_StructuredOutput/Agent_Step05_StructuredOutput.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step06_PersistedConversations/Agent_Step06_PersistedConversations.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step07_Observability/Agent_Step07_Observability.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step08_DependencyInjection/Agent_Step08_DependencyInjection.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step09_UsingMcpClientAsTools/Agent_Step09_UsingMcpClientAsTools.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step10_UsingImages/Agent_Step10_UsingImages.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step11_AsFunctionTool/Agent_Step11_AsFunctionTool.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step12_Middleware/Agent_Step12_Middleware.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step13_Plugins/Agent_Step13_Plugins.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step14_CodeInterpreter/Agent_Step14_CodeInterpreter.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step15_ComputerUse/Agent_Step15_ComputerUse.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step16_FileSearch/Agent_Step16_FileSearch.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step17_OpenAPITools/Agent_Step17_OpenAPITools.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step18_BingCustomSearch/Agent_Step18_BingCustomSearch.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step19_SharePoint/Agent_Step19_SharePoint.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step20_MicrosoftFabric/Agent_Step20_MicrosoftFabric.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step21_WebSearch/Agent_Step21_WebSearch.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step22_MemorySearch/Agent_Step22_MemorySearch.csproj" />
<Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step23_LocalMCP/Agent_Step23_LocalMCP.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AgentWithMemory/">
<File Path="samples/02-agents/AgentWithMemory/README.md" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/AgentWithMemory_Step01_ChatHistoryMemory.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/AgentWithMemory_Step02_MemoryUsingMem0.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/AgentWithMemory_Step04_MemoryUsingFoundry.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AgentWithOpenAI/">
<File Path="samples/02-agents/AgentWithOpenAI/README.md" />
@@ -171,6 +119,35 @@
<Project Path="samples/02-agents/AgentWithRAG/AgentWithRAG_Step03_CustomRAGDataSource/AgentWithRAG_Step03_CustomRAGDataSource.csproj" />
<Project Path="samples/02-agents/AgentWithRAG/AgentWithRAG_Step04_FoundryServiceRAG/AgentWithRAG_Step04_FoundryServiceRAG.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/FoundryAgents/">
<File Path="samples/02-agents/FoundryAgents/README.md" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Evaluations_Step01_RedTeaming/FoundryAgents_Evaluations_Step01_RedTeaming.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Evaluations_Step02_SelfReflection/FoundryAgents_Evaluations_Step02_SelfReflection.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step01.1_Basics/FoundryAgents_Step01.1_Basics.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step01.2_Running/FoundryAgents_Step01.2_Running.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step02_MultiturnConversation/FoundryAgents_Step02_MultiturnConversation.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step03_UsingFunctionTools/FoundryAgents_Step03_UsingFunctionTools.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step04_UsingFunctionToolsWithApprovals/FoundryAgents_Step04_UsingFunctionToolsWithApprovals.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step05_StructuredOutput/FoundryAgents_Step05_StructuredOutput.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step06_PersistedConversations/FoundryAgents_Step06_PersistedConversations.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step07_Observability/FoundryAgents_Step07_Observability.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step08_DependencyInjection/FoundryAgents_Step08_DependencyInjection.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step09_UsingMcpClientAsTools/FoundryAgents_Step09_UsingMcpClientAsTools.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step10_UsingImages/FoundryAgents_Step10_UsingImages.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step11_AsFunctionTool/FoundryAgents_Step11_AsFunctionTool.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step12_Middleware/FoundryAgents_Step12_Middleware.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step13_Plugins/FoundryAgents_Step13_Plugins.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step14_CodeInterpreter/FoundryAgents_Step14_CodeInterpreter.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step15_ComputerUse/FoundryAgents_Step15_ComputerUse.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step16_FileSearch/FoundryAgents_Step16_FileSearch.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step17_OpenAPITools/FoundryAgents_Step17_OpenAPITools.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step18_BingCustomSearch/FoundryAgents_Step18_BingCustomSearch.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step19_SharePoint/FoundryAgents_Step19_SharePoint.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step20_MicrosoftFabric/FoundryAgents_Step20_MicrosoftFabric.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step21_WebSearch/FoundryAgents_Step21_WebSearch.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step22_MemorySearch/FoundryAgents_Step22_MemorySearch.csproj" />
<Project Path="samples/02-agents/FoundryAgents/FoundryAgents_Step23_LocalMCP/FoundryAgents_Step23_LocalMCP.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/ModelContextProtocol/">
<File Path="samples/02-agents/ModelContextProtocol/README.md" />
<Project Path="samples/02-agents/ModelContextProtocol/Agent_MCP_Server/Agent_MCP_Server.csproj" />
@@ -307,18 +284,14 @@
</Folder>
<Folder Name="/Samples/05-end-to-end/HostedAgents/">
<Project Path="samples/05-end-to-end/HostedAgents/AgentsInWorkflows/AgentsInWorkflows.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentThreadAndHITL/AgentThreadAndHITL.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithHostedMCP/AgentWithHostedMCP.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithLocalTools/AgentWithLocalTools.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/AgentWithTextSearchRag/AgentWithTextSearchRag.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/FoundryMultiAgent/FoundryMultiAgent.csproj" />
<Project Path="samples/05-end-to-end/HostedAgents/FoundrySingleAgent/FoundrySingleAgent.csproj" />
</Folder>
<Folder Name="/Samples/05-end-to-end/AspNetAgentAuthorization/">
<File Path="samples/05-end-to-end/AspNetAgentAuthorization/docker-compose.yml" />
<File Path="samples/05-end-to-end/AspNetAgentAuthorization/README.md" />
<Project Path="samples/05-end-to-end/AspNetAgentAuthorization/RazorWebClient/RazorWebClient.csproj" />
<Project Path="samples/05-end-to-end/AspNetAgentAuthorization/Service/Service.csproj" />
<Project Path="samples/05-end-to-end/AspNetAgentAuthorization/RazorWebClient/RazorWebClient.csproj" />
</Folder>
<Folder Name="/Solution Items/">
<File Path=".editorconfig" />
@@ -338,6 +311,7 @@
</Folder>
<Folder Name="/Solution Items/.github/workflows/">
<File Path="../.github/workflows/dotnet-build-and-test.yml" />
<File Path="../.github/workflows/dotnet-check-coverage.ps1" />
<File Path="../.github/workflows/dotnet-format.yml" />
</Folder>
<Folder Name="/Solution Items/demos/">
@@ -374,10 +348,6 @@
<File Path="eng/MSBuild/Shared.props" />
<File Path="eng/MSBuild/Shared.targets" />
</Folder>
<Folder Name="/Solution Items/eng/scripts/">
<File Path="eng/scripts/dotnet-check-coverage.ps1" />
<File Path="eng/scripts/New-FilteredSolution.ps1" />
</Folder>
<Folder Name="/Solution Items/nuget/">
<File Path="nuget/icon.png" />
<File Path="nuget/nuget-package.props" />
@@ -443,10 +413,6 @@
<File Path="src/Shared/IntegrationTests/OpenAIConfiguration.cs" />
<File Path="src/Shared/IntegrationTests/README.md" />
</Folder>
<Folder Name="/Solution Items/src/Shared/IntegrationTestsAzureCredentials/">
<File Path="src/Shared/IntegrationTestsAzureCredentials/README.md" />
<File Path="src/Shared/IntegrationTestsAzureCredentials/TestAzureCliCredentials.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/Samples/">
<File Path="src/Shared/Samples/BaseSample.cs" />
<File Path="src/Shared/Samples/README.md" />
@@ -454,10 +420,6 @@
<File Path="src/Shared/Samples/TextOutputHelperExtensions.cs" />
<File Path="src/Shared/Samples/XunitLogger.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/Redaction/">
<File Path="src/Shared/Redaction/README.md" />
<File Path="src/Shared/Redaction/ReplacingRedactor.cs" />
</Folder>
<Folder Name="/Solution Items/src/Shared/Throw/">
<File Path="src/Shared/Throw/README.md" />
<File Path="src/Shared/Throw/Throw.cs" />
@@ -502,6 +464,8 @@
<Folder Name="/Tests/" />
<Folder Name="/Tests/IntegrationTests/">
<Project Path="tests/AgentConformance.IntegrationTests/AgentConformance.IntegrationTests.csproj" />
<Project Path="tests/AgentConversation.IntegrationTests/AgentConversation.IntegrationTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Abstractions.IntegrationTests/Microsoft.Agents.AI.Abstractions.IntegrationTests.csproj" />
<Project Path="tests/AnthropicChatCompletion.IntegrationTests/AnthropicChatCompletion.IntegrationTests.csproj" />
<Project Path="tests/AzureAI.IntegrationTests/AzureAI.IntegrationTests.csproj" />
<Project Path="tests/AzureAIAgentsPersistent.IntegrationTests/AzureAIAgentsPersistent.IntegrationTests.csproj" />
@@ -544,4 +508,4 @@
<Project Path="tests/Microsoft.Agents.AI.Workflows.Generators.UnitTests/Microsoft.Agents.AI.Workflows.Generators.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.UnitTests/Microsoft.Agents.AI.Workflows.UnitTests.csproj" />
</Folder>
</Solution>
</Solution>
-1
View File
@@ -14,7 +14,6 @@
"src\\Microsoft.Agents.AI.Declarative\\Microsoft.Agents.AI.Declarative.csproj",
"src\\Microsoft.Agents.AI.DevUI\\Microsoft.Agents.AI.DevUI.csproj",
"src\\Microsoft.Agents.AI.DurableTask\\Microsoft.Agents.AI.DurableTask.csproj",
"src\\Microsoft.Agents.AI.FoundryMemory\\Microsoft.Agents.AI.FoundryMemory.csproj",
"src\\Microsoft.Agents.AI.Hosting.A2A.AspNetCore\\Microsoft.Agents.AI.Hosting.A2A.AspNetCore.csproj",
"src\\Microsoft.Agents.AI.Hosting.A2A\\Microsoft.Agents.AI.Hosting.A2A.csproj",
"src\\Microsoft.Agents.AI.Hosting.AGUI.AspNetCore\\Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.csproj",
-6
View File
@@ -8,9 +8,6 @@
<ItemGroup Condition="'$(InjectSharedIntegrationTestCode)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\IntegrationTests\*.cs" LinkBase="Shared\IntegrationTests" />
</ItemGroup>
<ItemGroup Condition="'$(InjectSharedIntegrationTestAzureCredentialsCode)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\IntegrationTestsAzureCredentials\*.cs" LinkBase="Shared\IntegrationTestsAzureCredentials" />
</ItemGroup>
<ItemGroup Condition="'$(InjectSharedBuildTestCode)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\CodeTests\*.cs" LinkBase="Shared\CodeTests" />
</ItemGroup>
@@ -29,7 +26,4 @@
<ItemGroup Condition="'$(InjectSharedDiagnosticIds)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\DiagnosticIds\*.cs" LinkBase="Shared\DiagnosticIds" />
</ItemGroup>
<ItemGroup Condition="'$(InjectSharedRedaction)' == 'true'">
<Compile Include="$(MSBuildThisFileDirectory)\..\..\src\Shared\Redaction\*.cs" LinkBase="Shared\Redaction" />
</ItemGroup>
</Project>
-145
View File
@@ -1,145 +0,0 @@
#!/usr/bin/env pwsh
# Copyright (c) Microsoft. All rights reserved.
<#
.SYNOPSIS
Generates a filtered .slnx solution file by removing projects that don't match the specified criteria.
.DESCRIPTION
Parses a .slnx solution file and applies one or more filters:
- Removes projects that don't support the specified target framework (via MSBuild query).
- Optionally removes all sample projects (under samples/).
- Optionally filters test projects by name pattern (e.g., only *UnitTests*).
Writes the filtered solution to the specified output path and prints the path.
.PARAMETER Solution
Path to the source .slnx solution file.
.PARAMETER TargetFramework
The target framework to filter by (e.g., net10.0, net472).
.PARAMETER Configuration
Optional MSBuild configuration used when querying TargetFrameworks. Defaults to Debug.
.PARAMETER TestProjectNameFilter
Optional wildcard pattern to filter test project names (e.g., *UnitTests*, *IntegrationTests*).
When specified, only test projects whose filename matches this pattern are kept.
.PARAMETER ExcludeSamples
When specified, removes all projects under the samples/ directory from the solution.
.PARAMETER OutputPath
Optional output path for the filtered .slnx file. If not specified, a temp file is created.
.EXAMPLE
# Generate a filtered solution and run tests
$filtered = ./dotnet/eng/scripts/New-FilteredSolution.ps1 -Solution dotnet/agent-framework-dotnet.slnx -TargetFramework net472
dotnet test --solution $filtered --no-build -f net472
.EXAMPLE
# Generate a solution with only unit test projects
./dotnet/eng/scripts/New-FilteredSolution.ps1 -Solution dotnet/agent-framework-dotnet.slnx -TargetFramework net10.0 -TestProjectNameFilter "*UnitTests*" -OutputPath filtered-unit.slnx
.EXAMPLE
# Inline usage with dotnet test (PowerShell)
dotnet test --solution (./dotnet/eng/scripts/New-FilteredSolution.ps1 -Solution dotnet/agent-framework-dotnet.slnx -TargetFramework net472) --no-build -f net472
#>
[CmdletBinding()]
param(
[Parameter(Mandatory)]
[string]$Solution,
[Parameter(Mandatory)]
[string]$TargetFramework,
[string]$Configuration = "Debug",
[string]$TestProjectNameFilter,
[switch]$ExcludeSamples,
[string]$OutputPath
)
$ErrorActionPreference = "Stop"
# Resolve the solution path
$solutionPath = Resolve-Path $Solution
$solutionDir = Split-Path $solutionPath -Parent
if (-not $OutputPath) {
$OutputPath = [System.IO.Path]::Combine([System.IO.Path]::GetTempPath(), "filtered-$(Split-Path $solutionPath -Leaf)")
}
# Parse the .slnx XML
[xml]$slnx = Get-Content $solutionPath -Raw
$removed = @()
$kept = @()
# Remove sample projects if requested
if ($ExcludeSamples) {
$sampleProjects = $slnx.SelectNodes("//Project[contains(@Path, 'samples/')]")
foreach ($proj in $sampleProjects) {
$projRelPath = $proj.GetAttribute("Path")
Write-Verbose "Removing (sample): $projRelPath"
$removed += $projRelPath
$proj.ParentNode.RemoveChild($proj) | Out-Null
}
Write-Host "Removed $($sampleProjects.Count) sample project(s)." -ForegroundColor Yellow
}
# Filter all remaining projects by target framework
$allProjects = $slnx.SelectNodes("//Project")
foreach ($proj in $allProjects) {
$projRelPath = $proj.GetAttribute("Path")
$projFullPath = Join-Path $solutionDir $projRelPath
$projFileName = Split-Path $projRelPath -Leaf
$isTestProject = $projRelPath -like "*tests/*"
# Filter test projects by name pattern if specified
if ($isTestProject -and $TestProjectNameFilter -and ($projFileName -notlike $TestProjectNameFilter)) {
Write-Verbose "Removing (name filter): $projRelPath"
$removed += $projRelPath
$proj.ParentNode.RemoveChild($proj) | Out-Null
continue
}
if (-not (Test-Path $projFullPath)) {
Write-Verbose "Project not found, keeping in solution: $projRelPath"
$kept += $projRelPath
continue
}
# Query the project's target frameworks using MSBuild
$targetFrameworks = & dotnet msbuild $projFullPath -getProperty:TargetFrameworks -p:Configuration=$Configuration -nologo 2>$null
$targetFrameworks = $targetFrameworks.Trim()
if ($targetFrameworks -like "*$TargetFramework*") {
Write-Verbose "Keeping: $projRelPath (targets: $targetFrameworks)"
$kept += $projRelPath
}
else {
Write-Verbose "Removing: $projRelPath (targets: $targetFrameworks, missing: $TargetFramework)"
$removed += $projRelPath
$proj.ParentNode.RemoveChild($proj) | Out-Null
}
}
# Write the filtered solution
$slnx.Save($OutputPath)
# Report results to stderr so stdout is clean for piping
Write-Host "Filtered solution written to: $OutputPath" -ForegroundColor Green
if ($removed.Count -gt 0) {
Write-Host "Removed $($removed.Count) project(s):" -ForegroundColor Yellow
foreach ($r in $removed) {
Write-Host " - $r" -ForegroundColor Yellow
}
}
Write-Host "Kept $($kept.Count) project(s)." -ForegroundColor Green
# Output the path for piping
Write-Output $OutputPath
+1 -4
View File
@@ -1,10 +1,7 @@
{
"sdk": {
"version": "10.0.200",
"version": "10.0.100",
"rollForward": "minor",
"allowPrerelease": false
},
"test": {
"runner": "Microsoft.Testing.Platform"
}
}
+4 -4
View File
@@ -2,11 +2,11 @@
<PropertyGroup>
<!-- Central version prefix - applies to all nuget packages. -->
<VersionPrefix>1.0.0</VersionPrefix>
<RCNumber>4</RCNumber>
<RCNumber>2</RCNumber>
<PackageVersion Condition="'$(IsReleaseCandidate)' == 'true'">$(VersionPrefix)-rc$(RCNumber)</PackageVersion>
<PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' != ''">$(VersionPrefix)-$(VersionSuffix).260311.1</PackageVersion>
<PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' == ''">$(VersionPrefix)-preview.260311.1</PackageVersion>
<GitTag>1.0.0-rc4</GitTag>
<PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' != ''">$(VersionPrefix)-$(VersionSuffix).260225.1</PackageVersion>
<PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' == ''">$(VersionPrefix)-preview.260225.1</PackageVersion>
<GitTag>1.0.0-rc2</GitTag>
<Configurations>Debug;Release;Publish</Configurations>
<IsPackable>true</IsPackable>
@@ -4,6 +4,7 @@ using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hosting.AGUI.AspNetCore;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
WebApplicationBuilder builder = WebApplication.CreateBuilder(args);
@@ -26,7 +27,7 @@ ChatClient chatClient = new AzureOpenAIClient(
new DefaultAzureCredential())
.GetChatClient(deploymentName);
AIAgent agent = chatClient.AsAIAgent(
AIAgent agent = chatClient.AsIChatClient().AsAIAgent(
name: "AGUIAssistant",
instructions: "You are a helpful assistant.");
@@ -10,6 +10,7 @@
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -82,7 +82,7 @@ ChatClient chatClient = new AzureOpenAIClient(
new DefaultAzureCredential())
.GetChatClient(deploymentName);
ChatClientAgent agent = chatClient.AsAIAgent(
ChatClientAgent agent = chatClient.AsIChatClient().AsAIAgent(
name: "AGUIAssistant",
instructions: "You are a helpful assistant with access to restaurant information.",
tools: tools);
@@ -10,6 +10,7 @@
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -4,6 +4,7 @@ using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hosting.AGUI.AspNetCore;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
WebApplicationBuilder builder = WebApplication.CreateBuilder(args);
@@ -26,7 +27,7 @@ ChatClient chatClient = new AzureOpenAIClient(
new DefaultAzureCredential())
.GetChatClient(deploymentName);
AIAgent agent = chatClient.AsAIAgent(
AIAgent agent = chatClient.AsIChatClient().AsAIAgent(
name: "AGUIAssistant",
instructions: "You are a helpful assistant.");
@@ -10,6 +10,7 @@
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -59,18 +59,18 @@ while ((input = Console.ReadLine()) != null && !input.Equals("exit", StringCompa
{
switch (content)
{
case ToolApprovalRequestContent approvalRequest when approvalRequest.ToolCall is FunctionCallContent fcc:
DisplayApprovalRequest(approvalRequest, fcc);
case FunctionApprovalRequestContent approvalRequest:
DisplayApprovalRequest(approvalRequest);
Console.Write($"\nApprove '{fcc.Name}'? (yes/no): ");
Console.Write($"\nApprove '{approvalRequest.FunctionCall.Name}'? (yes/no): ");
string? userInput = Console.ReadLine();
bool approved = userInput?.ToUpperInvariant() is "YES" or "Y";
ToolApprovalResponseContent approvalResponse = approvalRequest.CreateResponse(approved);
FunctionApprovalResponseContent approvalResponse = approvalRequest.CreateResponse(approved);
if (approvalRequest.AdditionalProperties != null)
{
approvalResponse.AdditionalProperties = [];
approvalResponse.AdditionalProperties = new AdditionalPropertiesDictionary();
foreach (var kvp in approvalRequest.AdditionalProperties)
{
approvalResponse.AdditionalProperties[kvp.Key] = kvp.Value;
@@ -128,19 +128,19 @@ while ((input = Console.ReadLine()) != null && !input.Equals("exit", StringCompa
}
#pragma warning disable MEAI001
static void DisplayApprovalRequest(ToolApprovalRequestContent approvalRequest, FunctionCallContent fcc)
static void DisplayApprovalRequest(FunctionApprovalRequestContent approvalRequest)
{
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine();
Console.WriteLine("============================================================");
Console.WriteLine("APPROVAL REQUIRED");
Console.WriteLine("============================================================");
Console.WriteLine($"Function: {fcc.Name}");
Console.WriteLine($"Function: {approvalRequest.FunctionCall.Name}");
if (fcc.Arguments != null)
if (approvalRequest.FunctionCall.Arguments != null)
{
Console.WriteLine("Arguments:");
foreach (var arg in fcc.Arguments)
foreach (var arg in approvalRequest.FunctionCall.Arguments)
{
Console.WriteLine($" {arg.Key} = {arg.Value}");
}
@@ -9,7 +9,7 @@ using ServerFunctionApproval;
/// <summary>
/// A delegating agent that handles server function approval requests and responses.
/// Transforms between ToolApprovalRequestContent/ToolApprovalResponseContent
/// Transforms between FunctionApprovalRequestContent/FunctionApprovalResponseContent
/// and the server's request_approval tool call pattern.
/// </summary>
internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
@@ -50,14 +50,14 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
}
#pragma warning disable MEAI001 // Type is for evaluation purposes only
private static FunctionResultContent ConvertApprovalResponseToToolResult(ToolApprovalResponseContent approvalResponse, JsonSerializerOptions jsonOptions)
private static FunctionResultContent ConvertApprovalResponseToToolResult(FunctionApprovalResponseContent approvalResponse, JsonSerializerOptions jsonOptions)
{
return new FunctionResultContent(
callId: approvalResponse.RequestId,
callId: approvalResponse.Id,
result: JsonSerializer.SerializeToElement(
new ApprovalResponse
{
ApprovalId = approvalResponse.RequestId,
ApprovalId = approvalResponse.Id,
Approved = approvalResponse.Approved
},
jsonOptions));
@@ -89,7 +89,7 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
{
List<ChatMessage>? result = null;
Dictionary<string, ToolApprovalRequestContent> approvalRequests = [];
Dictionary<string, FunctionApprovalRequestContent> approvalRequests = [];
for (var messageIndex = 0; messageIndex < messages.Count; messageIndex++)
{
var message = messages[messageIndex];
@@ -102,21 +102,21 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
var content = message.Contents[contentIndex];
// Handle pending approval requests (transform to tool call)
if (content is ToolApprovalRequestContent approvalRequest &&
if (content is FunctionApprovalRequestContent approvalRequest &&
approvalRequest.AdditionalProperties?.TryGetValue("original_function", out var originalFunction) == true &&
originalFunction is FunctionCallContent original)
{
approvalRequests[approvalRequest.RequestId] = approvalRequest;
approvalRequests[approvalRequest.Id] = approvalRequest;
transformedContents ??= CopyContentsUpToIndex(message.Contents, contentIndex);
transformedContents.Add(original);
}
// Handle pending approval responses (transform to tool result)
else if (content is ToolApprovalResponseContent approvalResponse &&
approvalRequests.TryGetValue(approvalResponse.RequestId, out var correspondingRequest))
else if (content is FunctionApprovalResponseContent approvalResponse &&
approvalRequests.TryGetValue(approvalResponse.Id, out var correspondingRequest))
{
transformedContents ??= CopyContentsUpToIndex(message.Contents, contentIndex);
transformedContents.Add(ConvertApprovalResponseToToolResult(approvalResponse, jsonSerializerOptions));
approvalRequests.Remove(approvalResponse.RequestId);
approvalRequests.Remove(approvalResponse.Id);
correspondingRequest.AdditionalProperties?.Remove("original_function");
}
// Skip historical approval content
@@ -131,9 +131,9 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
transformedContents ??= CopyContentsUpToIndex(message.Contents, contentIndex);
approvalCalls.Remove(functionResult.CallId);
}
else
else if (transformedContents != null)
{
transformedContents?.Add(content);
transformedContents.Add(content);
}
}
@@ -155,10 +155,10 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
result ??= CopyMessagesUpToIndex(messages, messageIndex);
result.Add(newMessage);
}
else
else if (result != null)
{
// We're already copying messages, so copy this unchanged message too
result?.Add(message);
result.Add(message);
}
// If result is null, we haven't made any changes yet, so keep processing
}
@@ -198,8 +198,8 @@ internal sealed class ServerFunctionApprovalClientAgent : DelegatingAIAgent
var functionCallArgs = (Dictionary<string, object?>?)approvalRequest.FunctionArguments?
.Deserialize(jsonSerializerOptions.GetTypeInfo(typeof(Dictionary<string, object?>)));
var approvalRequestContent = new ToolApprovalRequestContent(
requestId: approvalRequest.ApprovalId,
var approvalRequestContent = new FunctionApprovalRequestContent(
id: approvalRequest.ApprovalId,
new FunctionCallContent(
callId: approvalRequest.ApprovalId,
name: approvalRequest.FunctionName,
@@ -60,7 +60,7 @@ ChatClient openAIChatClient = new AzureOpenAIClient(
new DefaultAzureCredential())
.GetChatClient(deploymentName);
ChatClientAgent baseAgent = openAIChatClient.AsAIAgent(
ChatClientAgent baseAgent = openAIChatClient.AsIChatClient().AsAIAgent(
name: "AGUIAssistant",
instructions: "You are a helpful assistant in charge of approving expenses",
tools: tools);
@@ -10,6 +10,7 @@
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -9,7 +9,7 @@ using ServerFunctionApproval;
/// <summary>
/// A delegating agent that handles function approval requests on the server side.
/// Transforms between ToolApprovalRequestContent/ToolApprovalResponseContent
/// Transforms between FunctionApprovalRequestContent/FunctionApprovalResponseContent
/// and the request_approval tool call pattern for client communication.
/// </summary>
internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
@@ -50,32 +50,44 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
}
#pragma warning disable MEAI001 // Type is for evaluation purposes only
private static ToolApprovalRequestContent ConvertToolCallToApprovalRequest(FunctionCallContent toolCall, JsonSerializerOptions jsonSerializerOptions)
private static FunctionApprovalRequestContent ConvertToolCallToApprovalRequest(FunctionCallContent toolCall, JsonSerializerOptions jsonSerializerOptions)
{
if (toolCall.Name != "request_approval" || toolCall.Arguments == null)
{
throw new InvalidOperationException("Invalid request_approval tool call");
}
var request = (toolCall.Arguments.TryGetValue("request", out var reqObj) &&
var request = toolCall.Arguments.TryGetValue("request", out var reqObj) &&
reqObj is JsonElement argsElement &&
argsElement.Deserialize(jsonSerializerOptions.GetTypeInfo(typeof(ApprovalRequest))) is ApprovalRequest approvalRequest &&
approvalRequest != null ? approvalRequest : null) ?? throw new InvalidOperationException("Failed to deserialize approval request from tool call");
return new ToolApprovalRequestContent(
requestId: request.ApprovalId,
approvalRequest != null ? approvalRequest : null;
if (request == null)
{
throw new InvalidOperationException("Failed to deserialize approval request from tool call");
}
return new FunctionApprovalRequestContent(
id: request.ApprovalId,
new FunctionCallContent(
callId: request.ApprovalId,
name: request.FunctionName,
arguments: request.FunctionArguments));
}
private static ToolApprovalResponseContent ConvertToolResultToApprovalResponse(FunctionResultContent result, ToolApprovalRequestContent approval, JsonSerializerOptions jsonSerializerOptions)
private static FunctionApprovalResponseContent ConvertToolResultToApprovalResponse(FunctionResultContent result, FunctionApprovalRequestContent approval, JsonSerializerOptions jsonSerializerOptions)
{
var approvalResponse = (result.Result is JsonElement je ?
var approvalResponse = result.Result is JsonElement je ?
(ApprovalResponse?)je.Deserialize(jsonSerializerOptions.GetTypeInfo(typeof(ApprovalResponse))) :
result.Result is string str ?
(ApprovalResponse?)JsonSerializer.Deserialize(str, jsonSerializerOptions.GetTypeInfo(typeof(ApprovalResponse))) :
result.Result as ApprovalResponse) ?? throw new InvalidOperationException("Failed to deserialize approval response from tool result");
result.Result as ApprovalResponse;
if (approvalResponse == null)
{
throw new InvalidOperationException("Failed to deserialize approval response from tool result");
}
return approval.CreateResponse(approvalResponse.Approved);
}
#pragma warning restore MEAI001
@@ -109,7 +121,7 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
// Track approval ID to original call ID mapping
_ = new Dictionary<string, string>();
#pragma warning disable MEAI001 // Type is for evaluation purposes only and is subject to change or removal in future updates. Suppress this diagnostic to proceed.
Dictionary<string, ToolApprovalRequestContent> trackedRequestApprovalToolCalls = []; // Remote approvals
Dictionary<string, FunctionApprovalRequestContent> trackedRequestApprovalToolCalls = new(); // Remote approvals
for (int messageIndex = 0; messageIndex < messages.Count; messageIndex++)
{
var message = messages[messageIndex];
@@ -134,7 +146,7 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
});
}
else if (content is FunctionResultContent toolResult &&
trackedRequestApprovalToolCalls.TryGetValue(toolResult.CallId, out var approval))
trackedRequestApprovalToolCalls.TryGetValue(toolResult.CallId, out var approval) == true)
{
result ??= CopyMessagesUpToIndex(messages, messageIndex);
transformedContents ??= CopyContentsUpToIndex(message.Contents, j);
@@ -149,9 +161,9 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
AdditionalProperties = message.AdditionalProperties
});
}
else
else if (result != null)
{
result?.Add(message);
result.Add(message);
}
}
}
@@ -169,10 +181,11 @@ internal sealed class ServerFunctionApprovalAgent : DelegatingAIAgent
{
var content = update.Contents[i];
#pragma warning disable MEAI001 // Type is for evaluation purposes only
if (content is ToolApprovalRequestContent request && request.ToolCall is FunctionCallContent functionCall)
if (content is FunctionApprovalRequestContent request)
{
updatedContents ??= [.. update.Contents];
var approvalId = request.RequestId;
var functionCall = request.FunctionCall;
var approvalId = request.Id;
var approvalData = new ApprovalRequest
{
@@ -72,9 +72,10 @@ internal sealed class StatefulAgent<TState> : DelegatingAIAgent
if (content is DataContent dataContent && dataContent.MediaType == "application/json")
{
// Deserialize the state
if (JsonSerializer.Deserialize(
TState? newState = JsonSerializer.Deserialize(
dataContent.Data.Span,
this._jsonSerializerOptions.GetTypeInfo(typeof(TState))) is TState newState)
this._jsonSerializerOptions.GetTypeInfo(typeof(TState))) as TState;
if (newState != null)
{
this.State = newState;
}
@@ -4,6 +4,7 @@ using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hosting.AGUI.AspNetCore;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.Options;
using OpenAI.Chat;
using RecipeAssistant;
@@ -36,7 +37,7 @@ ChatClient chatClient = new AzureOpenAIClient(
new DefaultAzureCredential())
.GetChatClient(deploymentName);
AIAgent baseAgent = chatClient.AsAIAgent(
AIAgent baseAgent = chatClient.AsIChatClient().AsAIAgent(
name: "RecipeAgent",
instructions: """
You are a helpful recipe assistant. When users ask you to create or suggest a recipe,
@@ -10,6 +10,7 @@
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
@@ -18,7 +18,6 @@ using OpenTelemetry.Trace;
#region Setup Telemetry
// Source name for this sample's custom ActivitySource and Meter; other instrumentation uses their own sources/categories.
const string SourceName = "OpenTelemetryAspire.ConsoleApp";
const string ServiceName = "AgentOpenTelemetry";
@@ -41,6 +40,7 @@ var resource = ResourceBuilder.CreateDefault()
var tracerProviderBuilder = Sdk.CreateTracerProviderBuilder()
.SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
.AddSource(SourceName) // Our custom activity source
.AddSource("*Microsoft.Agents.AI") // Agent Framework telemetry
.AddHttpClientInstrumentation() // Capture HTTP calls to OpenAI
.AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint));
@@ -54,7 +54,8 @@ using var tracerProvider = tracerProviderBuilder.Build();
// Setup metrics with resource and instrument name filtering
using var meterProvider = Sdk.CreateMeterProviderBuilder()
.SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
.AddMeter(SourceName) // Our custom meter source
.AddMeter(SourceName) // Our custom meter
.AddMeter("*Microsoft.Agents.AI") // Agent Framework metrics
.AddHttpClientInstrumentation() // HTTP client metrics
.AddRuntimeInstrumentation() // .NET runtime metrics
.AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint))
@@ -127,7 +128,7 @@ var agent = new ChatClientAgent(instrumentedChatClient,
instructions: "You are a helpful assistant that provides concise and informative responses.",
tools: [AIFunctionFactory.Create(GetWeatherAsync)])
.AsBuilder()
.UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
.UseOpenTelemetry(SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
.Build();
var session = await agent.CreateSessionAsync();
@@ -1,7 +1,5 @@
// Copyright (c) Microsoft. All rights reserved.
#pragma warning disable CS0618 // Type or member is obsolete - sample uses deprecated PersistentAgentsClientExtensions
// This sample shows how to create and use a simple AI agent with Azure Foundry Agents as the backend.
using Azure.AI.Agents.Persistent;
@@ -3,10 +3,9 @@
// This sample shows how to create and use a AI agents with Azure Foundry Agents as the backend.
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Azure.AI.Projects.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
@@ -31,18 +30,14 @@ var createdAgentVersion = aiProjectClient.Agents.CreateAgentVersion(agentName: J
// agentVersion.Name = <agentName>
// You can use an AIAgent with an already created server side agent version.
FoundryAgent existingJokerAgent = aiProjectClient.AsAIAgent(createdAgentVersion);
AIAgent existingJokerAgent = aiProjectClient.AsAIAgent(createdAgentVersion);
// You can also create another AIAgent version by providing the same name with a different definition.
AgentVersion newJokerAgentVersion = await aiProjectClient.Agents.CreateAgentVersionAsync(
JokerName,
new AgentVersionCreationOptions(new PromptAgentDefinition(model: deploymentName) { Instructions = "You are extremely hilarious at telling jokes." }));
FoundryAgent newJokerAgent = aiProjectClient.AsAIAgent(newJokerAgentVersion);
AIAgent newJokerAgent = await aiProjectClient.CreateAIAgentAsync(name: JokerName, model: deploymentName, instructions: "You are extremely hilarious at telling jokes.");
// You can also get the AIAgent latest version just providing its name.
AgentRecord jokerAgentRecord = await aiProjectClient.Agents.GetAgentAsync(JokerName);
FoundryAgent jokerAgentLatest = aiProjectClient.AsAIAgent(jokerAgentRecord);
AgentVersion latestAgentVersion = jokerAgentRecord.GetLatestVersion();
AIAgent jokerAgentLatest = await aiProjectClient.GetAIAgentAsync(name: JokerName);
var latestAgentVersion = jokerAgentLatest.GetService<AgentVersion>()!;
// The AIAgent version can be accessed via the GetService method.
Console.WriteLine($"Latest agent version id: {latestAgentVersion.Id}");
@@ -17,8 +17,8 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "Joker");
.GetResponsesClient(deploymentName)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
@@ -29,8 +29,8 @@ Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
AIAgent agentStoreFalse = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.AsIChatClientWithStoredOutputDisabled(model: deploymentName)
.GetResponsesClient(deploymentName)
.AsIChatClientWithStoredOutputDisabled()
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
@@ -9,7 +9,7 @@
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Abstractions\Microsoft.Agents.AI.Abstractions.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
</Project>
@@ -11,8 +11,8 @@ var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt
AIAgent agent = new OpenAIClient(
apiKey)
.GetResponsesClient()
.AsAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
.GetResponsesClient(model)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
@@ -14,10 +14,6 @@
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<Compile Include="..\SubprocessScriptRunner.cs" Link="SubprocessScriptRunner.cs" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
@@ -0,0 +1,49 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use Agent Skills with a ChatClientAgent.
// Agent Skills are modular packages of instructions and resources that extend an agent's capabilities.
// Skills follow the progressive disclosure pattern: advertise -> load -> read resources.
//
// This sample includes the expense-report skill:
// - Policy-based expense filing with references and assets
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
// --- Skills Provider ---
// Discovers skills from the 'skills' directory and makes them available to the agent
var skillsProvider = new FileAgentSkillsProvider(skillPath: Path.Combine(AppContext.BaseDirectory, "skills"));
// --- Agent Setup ---
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
Name = "SkillsAgent",
ChatOptions = new()
{
Instructions = "You are a helpful assistant.",
},
AIContextProviders = [skillsProvider],
});
// --- Example 1: Expense policy question (loads FAQ resource) ---
Console.WriteLine("Example 1: Checking expense policy FAQ");
Console.WriteLine("---------------------------------------");
AgentResponse response1 = await agent.RunAsync("Are tips reimbursable? I left a 25% tip on a taxi ride and want to know if that's covered.");
Console.WriteLine($"Agent: {response1.Text}\n");
// --- Example 2: Filing an expense report (multi-turn with template asset) ---
Console.WriteLine("Example 2: Filing an expense report");
Console.WriteLine("---------------------------------------");
AgentSession session = await agent.CreateSessionAsync();
AgentResponse response2 = await agent.RunAsync("I had 3 client dinners and a $1,200 flight last week. Return a draft expense report and ask about any missing details.",
session);
Console.WriteLine($"Agent: {response2.Text}\n");
@@ -0,0 +1,63 @@
# Agent Skills Sample
This sample demonstrates how to use **Agent Skills** with a `ChatClientAgent` in the Microsoft Agent Framework.
## What are Agent Skills?
Agent Skills are modular packages of instructions and resources that enable AI agents to perform specialized tasks. They follow the [Agent Skills specification](https://agentskills.io/) and implement the progressive disclosure pattern:
1. **Advertise**: Skills are advertised with name + description (~100 tokens per skill)
2. **Load**: Full instructions are loaded on-demand via `load_skill` tool
3. **Resources**: References and other files loaded via `read_skill_resource` tool
## Skills Included
### expense-report
Policy-based expense filing with spending limits, receipt requirements, and approval workflows.
- `references/POLICY_FAQ.md` — Detailed expense policy Q&A
- `assets/expense-report-template.md` — Submission template
## Project Structure
```
Agent_Step01_BasicSkills/
├── Program.cs
├── Agent_Step01_BasicSkills.csproj
└── skills/
└── expense-report/
├── SKILL.md
├── references/
│ └── POLICY_FAQ.md
└── assets/
└── expense-report-template.md
```
## Running the Sample
### Prerequisites
- .NET 10.0 SDK
- Azure OpenAI endpoint with a deployed model
### Setup
1. Set environment variables:
```bash
export AZURE_OPENAI_ENDPOINT="https://your-endpoint.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"
```
2. Run the sample:
```bash
dotnet run
```
### Examples
The sample runs two examples:
1. **Expense policy FAQ** — Asks about tip reimbursement; the agent loads the expense-report skill and reads the FAQ resource
2. **Filing an expense report** — Multi-turn conversation to draft an expense report using the template asset
## Learn More
- [Agent Skills Specification](https://agentskills.io/)
- [Microsoft Agent Framework Documentation](../../../../../docs/)
@@ -0,0 +1,40 @@
---
name: expense-report
description: File and validate employee expense reports according to Contoso company policy. Use when asked about expense submissions, reimbursement rules, receipt requirements, spending limits, or expense categories.
metadata:
author: contoso-finance
version: "2.1"
---
# Expense Report
## Categories and Limits
| Category | Limit | Receipt | Approval |
|---|---|---|---|
| Meals — solo | $50/day | >$25 | No |
| Meals — team/client | $75/person | Always | Manager if >$200 total |
| Lodging | $250/night | Always | Manager if >3 nights |
| Ground transport | $100/day | >$15 | No |
| Airfare | Economy | Always | Manager; VP if >$1,500 |
| Conference/training | $2,000/event | Always | Manager + L&D |
| Office supplies | $100 | Yes | No |
| Software/subscriptions | $50/month | Yes | Manager if >$200/year |
## Filing Process
1. Collect receipts — must show vendor, date, amount, payment method.
2. Categorize per table above.
3. Use template: [assets/expense-report-template.md](assets/expense-report-template.md).
4. For client/team meals: list attendee names and business purpose.
5. Submit — auto-approved if <$500; manager if $500$2,000; VP if >$2,000.
6. Reimbursement: 10 business days via direct deposit.
## Policy Rules
- Submit within 30 days of transaction.
- Alcohol is never reimbursable.
- Foreign currency: convert to USD at transaction-date rate; note original currency and amount.
- Mixed personal/business travel: only business portion reimbursable; provide comparison quotes.
- Lost receipts (>$25): file Lost Receipt Affidavit from Finance. Max 2 per quarter.
- For policy questions not covered above, consult the FAQ: [references/POLICY_FAQ.md](references/POLICY_FAQ.md). Answers should be based on what this document and the FAQ state.
@@ -0,0 +1,5 @@
# Expense Report Template
| Date | Category | Vendor | Description | Amount (USD) | Original Currency | Original Amount | Attendees | Business Purpose | Receipt Attached |
|------|----------|--------|-------------|--------------|-------------------|-----------------|-----------|------------------|------------------|
| | | | | | | | | | Yes or No |
@@ -0,0 +1,55 @@
# Expense Policy — Frequently Asked Questions
## Meals
**Q: Can I expense coffee or snacks during the workday?**
A: Daily coffee/snacks under $10 are not reimbursable (considered personal). Coffee purchased during a client meeting or team working session is reimbursable as a team meal.
**Q: What if a team dinner exceeds the per-person limit?**
A: The $75/person limit applies as a guideline. Overages up to 20% are accepted with a written justification (e.g., "client dinner at venue chosen by client"). Overages beyond 20% require pre-approval from your VP.
**Q: Do I need to list every attendee?**
A: Yes. For client meals, list the client's name and company. For team meals, list all employee names. For groups over 10, you may attach a separate attendee list.
## Travel
**Q: Can I book a premium economy or business class flight?**
A: Economy class is the standard. Premium economy is allowed for flights over 6 hours. Business class requires VP pre-approval and is generally reserved for flights over 10 hours or medical accommodation.
**Q: What about ride-sharing (Uber/Lyft) vs. rental cars?**
A: Use ride-sharing for trips under 30 miles round-trip. Rent a car for multi-day travel or when ride-sharing would exceed $100/day. Always choose the compact/standard category unless traveling with 3+ people.
**Q: Are tips reimbursable?**
A: Tips up to 20% are reimbursable for meals, taxi/ride-share, and hotel housekeeping. Tips above 20% require justification.
## Lodging
**Q: What if the $250/night limit isn't enough for the city I'm visiting?**
A: For high-cost cities (New York, San Francisco, London, Tokyo, Sydney), the limit is automatically increased to $350/night. No additional approval is needed. For other locations where rates are unusually high (e.g., during a major conference), request a per-trip exception from your manager before booking.
**Q: Can I stay with friends/family instead and get a per-diem?**
A: No. Contoso reimburses actual lodging costs only, not per-diems.
## Subscriptions and Software
**Q: Can I expense a personal productivity tool?**
A: Software must be directly related to your job function. Tools like IDE licenses, design software, or project management apps are reimbursable. General productivity apps (note-taking, personal calendar) are not, unless your manager confirms a business need in writing.
**Q: What about annual subscriptions?**
A: Annual subscriptions over $200 require manager approval before purchase. Submit the approval email with your expense report.
## Receipts and Documentation
**Q: My receipt is faded/damaged. What do I do?**
A: Try to obtain a duplicate from the vendor. If not possible, submit a Lost Receipt Affidavit (available from the Finance SharePoint site). You're limited to 2 affidavits per quarter.
**Q: Do I need a receipt for parking meters or tolls?**
A: For amounts under $15, no receipt is required — just note the date, location, and amount. For $15 and above, a receipt or bank/credit card statement excerpt is required.
## Approval and Reimbursement
**Q: My manager is on leave. Who approves my report?**
A: Expense reports can be approved by your skip-level manager or any manager designated as an alternate approver in the expense system.
**Q: Can I submit expenses from a previous quarter?**
A: The standard 30-day window applies. Expenses older than 30 days require a written explanation and VP approval. Expenses older than 90 days are not reimbursable except in extraordinary circumstances (extended leave, medical emergency) with CFO approval.
@@ -1,48 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use file-based Agent Skills with a ChatClientAgent.
// Skills are discovered from SKILL.md files on disk and follow the progressive disclosure pattern:
// 1. Advertise — skill names and descriptions in the system prompt
// 2. Load — full instructions loaded on demand via load_skill tool
// 3. Read resources — reference files read via read_skill_resource tool
// 4. Run scripts — scripts executed via run_skill_script tool with a subprocess executor
//
// This sample uses a unit-converter skill that converts between miles, kilometers, pounds, and kilograms.
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
// --- Skills Provider ---
// Discovers skills from the 'skills' directory containing SKILL.md files.
// The script runner runs file-based scripts (e.g. Python) as local subprocesses.
var skillsProvider = new AgentSkillsProvider(
Path.Combine(AppContext.BaseDirectory, "skills"),
SubprocessScriptRunner.RunAsync);
// --- Agent Setup ---
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
// --- Example: Unit conversion ---
Console.WriteLine("Converting units with file-based skills");
Console.WriteLine(new string('-', 60));
AgentResponse response = await agent.RunAsync(
"How many kilometers is a marathon (26.2 miles)? And how many pounds is 75 kilograms?");
Console.WriteLine($"Agent: {response.Text}");
@@ -1,51 +0,0 @@
# File-Based Agent Skills Sample
This sample demonstrates how to use **file-based Agent Skills** with a `ChatClientAgent`.
## What it demonstrates
- Discovering skills from `SKILL.md` files on disk via `AgentFileSkillsSource`
- The progressive disclosure pattern: advertise → load → read resources → run scripts
- Using the `AgentSkillsProvider` constructor with a skill directory path and script executor
- Running file-based scripts (Python) via a subprocess-based executor
## Skills Included
### unit-converter
Converts between common units (miles↔km, pounds↔kg) using a multiplication factor.
- `references/conversion-table.md` — Conversion factor table
- `scripts/convert.py` — Python script that performs the conversion
## Running the Sample
### Prerequisites
- .NET 10.0 SDK
- Azure OpenAI endpoint with a deployed model
- Python 3 installed and available as `python3` on your PATH
### Setup
```bash
export AZURE_OPENAI_ENDPOINT="https://your-endpoint.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"
```
### Run
```bash
dotnet run
```
### Expected Output
```
Converting units with file-based skills
------------------------------------------------------------
Agent: Here are your conversions:
1. **26.2 miles → 42.16 km** (a marathon distance)
2. **75 kg → 165.35 lbs**
```
@@ -1,11 +0,0 @@
---
name: unit-converter
description: Convert between common units using a multiplication factor. Use when asked to convert miles, kilometers, pounds, or kilograms.
---
## Usage
When the user requests a unit conversion:
1. First, review `references/conversion-table.md` to find the correct factor
2. Run the `scripts/convert.py` script with `--value <number> --factor <factor>` (e.g. `--value 26.2 --factor 1.60934`)
3. Present the converted value clearly with both units
@@ -1,10 +0,0 @@
# Conversion Tables
Formula: **result = value × factor**
| From | To | Factor |
|-------------|-------------|----------|
| miles | kilometers | 1.60934 |
| kilometers | miles | 0.621371 |
| pounds | kilograms | 0.453592 |
| kilograms | pounds | 2.20462 |
@@ -1,29 +0,0 @@
# Unit conversion script
# Converts a value using a multiplication factor: result = value × factor
#
# Usage:
# python scripts/convert.py --value 26.2 --factor 1.60934
# python scripts/convert.py --value 75 --factor 2.20462
import argparse
import json
def main() -> None:
parser = argparse.ArgumentParser(
description="Convert a value using a multiplication factor.",
epilog="Examples:\n"
" python scripts/convert.py --value 26.2 --factor 1.60934\n"
" python scripts/convert.py --value 75 --factor 2.20462",
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.add_argument("--value", type=float, required=True, help="The numeric value to convert.")
parser.add_argument("--factor", type=float, required=True, help="The conversion factor from the table.")
args = parser.parse_args()
result = round(args.value * args.factor, 4)
print(json.dumps({"value": args.value, "factor": args.factor, "result": result}))
if __name__ == "__main__":
main()
@@ -4,4 +4,4 @@ Samples demonstrating Agent Skills capabilities.
| Sample | Description |
|--------|-------------|
| [Agent_Step01_FileBasedSkills](Agent_Step01_FileBasedSkills/) | Define skills as `SKILL.md` files on disk with reference documents. Uses a unit-converter skill. |
| [Agent_Step01_BasicSkills](Agent_Step01_BasicSkills/) | Using Agent Skills with a ChatClientAgent, including progressive disclosure and skill resources |
@@ -1,137 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
// Sample subprocess-based skill script runner.
// Executes file-based skill scripts as local subprocesses.
// This is provided for demonstration purposes only.
using System.Diagnostics;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
/// <summary>
/// Executes file-based skill scripts as local subprocesses.
/// </summary>
/// <remarks>
/// This runner uses the script's absolute path, converts the arguments
/// to CLI flags, and returns captured output. It is intended for
/// demonstration purposes only.
/// </remarks>
internal static class SubprocessScriptRunner
{
/// <summary>
/// Runs a skill script as a local subprocess.
/// </summary>
public static async Task<object?> RunAsync(
AgentFileSkill skill,
AgentFileSkillScript script,
AIFunctionArguments arguments,
CancellationToken cancellationToken)
{
if (!File.Exists(script.FullPath))
{
return $"Error: Script file not found: {script.FullPath}";
}
string extension = Path.GetExtension(script.FullPath);
string? interpreter = extension switch
{
".py" => "python3",
".js" => "node",
".sh" => "bash",
".ps1" => "pwsh",
_ => null,
};
var startInfo = new ProcessStartInfo
{
RedirectStandardOutput = true,
RedirectStandardError = true,
UseShellExecute = false,
CreateNoWindow = true,
WorkingDirectory = Path.GetDirectoryName(script.FullPath) ?? ".",
};
if (interpreter is not null)
{
startInfo.FileName = interpreter;
startInfo.ArgumentList.Add(script.FullPath);
}
else
{
startInfo.FileName = script.FullPath;
}
if (arguments is not null)
{
foreach (var (key, value) in arguments)
{
if (value is bool boolValue)
{
if (boolValue)
{
startInfo.ArgumentList.Add(NormalizeKey(key));
}
}
else if (value is not null)
{
startInfo.ArgumentList.Add(NormalizeKey(key));
startInfo.ArgumentList.Add(value.ToString()!);
}
}
}
Process? process = null;
try
{
process = Process.Start(startInfo);
if (process is null)
{
return $"Error: Failed to start process for script '{script.Name}'.";
}
Task<string> outputTask = process.StandardOutput.ReadToEndAsync(cancellationToken);
Task<string> errorTask = process.StandardError.ReadToEndAsync(cancellationToken);
await process.WaitForExitAsync(cancellationToken).ConfigureAwait(false);
string output = await outputTask.ConfigureAwait(false);
string error = await errorTask.ConfigureAwait(false);
if (!string.IsNullOrEmpty(error))
{
output += $"\nStderr:\n{error}";
}
if (process.ExitCode != 0)
{
output += $"\nScript exited with code {process.ExitCode}";
}
return string.IsNullOrEmpty(output) ? "(no output)" : output.Trim();
}
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
{
// Kill the process on cancellation to avoid leaving orphaned subprocesses.
process?.Kill(entireProcessTree: true);
throw;
}
catch (OperationCanceledException)
{
throw;
}
catch (Exception ex)
{
return $"Error: Failed to execute script '{script.Name}': {ex.Message}";
}
finally
{
process?.Dispose();
}
}
/// <summary>
/// Normalizes a parameter key to a consistent --flag format.
/// Models may return keys with or without leading dashes (e.g., "value" vs "--value").
/// </summary>
private static string NormalizeKey(string key) => "--" + key.TrimStart('-');
}
@@ -5,13 +5,20 @@
using Anthropic;
using Anthropic.Core;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
AIAgent agent =
new AnthropicClient(new ClientOptions { ApiKey = apiKey })
AIAgent agent = new AnthropicClient(new ClientOptions { ApiKey = apiKey })
.AsAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
var response = await agent.RunAsync("Tell me a joke about a pirate.");
Console.WriteLine(response);
// Invoke the agent with streaming support.
await foreach (var update in agent.RunStreamingAsync("Tell me a joke about a pirate."))
{
Console.WriteLine(update);
}
@@ -11,7 +11,6 @@ using System.Text.Json;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;
using Microsoft.Agents.AI.FoundryMemory;
string foundryEndpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
@@ -20,9 +19,6 @@ string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLO
string embeddingModelName = Environment.GetEnvironmentVariable("AZURE_AI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-ada-002";
// Create an AIProjectClient for Foundry with Azure Identity authentication.
// 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.
DefaultAzureCredential credential = new();
AIProjectClient projectClient = new(new Uri(foundryEndpoint), credential);
@@ -37,15 +33,11 @@ FoundryMemoryProvider memoryProvider = new(
memoryStoreName,
stateInitializer: _ => new(new FoundryMemoryProviderScope("sample-user-123")));
FoundryAgent agent = projectClient.AsAIAgent(
new ChatClientAgentOptions()
AIAgent agent = await projectClient.CreateAIAgentAsync(deploymentName,
options: new ChatClientAgentOptions()
{
Name = "TravelAssistantWithFoundryMemory",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details."
},
ChatOptions = new() { Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details." },
AIContextProviders = [memoryProvider]
});
@@ -1,22 +0,0 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFrameworks>net10.0</TargetFrameworks>
<Nullable>enable</Nullable>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
</Project>
@@ -1,133 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
namespace SampleApp;
/// <summary>
/// A <see cref="ChatHistoryProvider"/> that keeps a bounded window of recent messages in session state
/// (via <see cref="InMemoryChatHistoryProvider"/>) and overflows older messages to a vector store
/// (via <see cref="ChatHistoryMemoryProvider"/>). When providing chat history, it searches the vector
/// store for relevant older messages and prepends them as a memory context message.
/// </summary>
/// <remarks>
/// Only non-system messages are counted towards the session state limit and overflow mechanism. System messages are always retained in session state and are not included in the vector store.
/// Function calls and function results are also dropped when truncation happens, both from in-memory state, and they are also not persisted to the vector store.
/// </remarks>
internal sealed class BoundedChatHistoryProvider : ChatHistoryProvider, IDisposable
{
private readonly InMemoryChatHistoryProvider _chatHistoryProvider;
private readonly ChatHistoryMemoryProvider _memoryProvider;
private readonly TruncatingChatReducer _reducer;
private readonly string _contextPrompt;
private IReadOnlyList<string>? _stateKeys;
/// <summary>
/// Initializes a new instance of the <see cref="BoundedChatHistoryProvider"/> class.
/// </summary>
/// <param name="maxSessionMessages">The maximum number of non-system messages to keep in session state before overflowing to the vector store.</param>
/// <param name="vectorStore">The vector store to use for storing and retrieving overflow chat history.</param>
/// <param name="collectionName">The name of the collection for storing overflow chat history in the vector store.</param>
/// <param name="vectorDimensions">The number of dimensions to use for the chat history vector store embeddings.</param>
/// <param name="stateInitializer">A delegate that initializes the memory provider state, providing the storage and search scopes.</param>
/// <param name="contextPrompt">Optional prompt to prefix memory search results. Defaults to a standard memory context prompt.</param>
public BoundedChatHistoryProvider(
int maxSessionMessages,
VectorStore vectorStore,
string collectionName,
int vectorDimensions,
Func<AgentSession?, ChatHistoryMemoryProvider.State> stateInitializer,
string? contextPrompt = null)
{
if (maxSessionMessages < 0)
{
throw new ArgumentOutOfRangeException(nameof(maxSessionMessages), "maxSessionMessages must be non-negative.");
}
this._reducer = new TruncatingChatReducer(maxSessionMessages);
this._chatHistoryProvider = new InMemoryChatHistoryProvider(new InMemoryChatHistoryProviderOptions
{
ChatReducer = this._reducer,
ReducerTriggerEvent = InMemoryChatHistoryProviderOptions.ChatReducerTriggerEvent.AfterMessageAdded,
StorageInputRequestMessageFilter = msgs => msgs,
});
this._memoryProvider = new ChatHistoryMemoryProvider(
vectorStore,
collectionName,
vectorDimensions,
stateInitializer,
options: new ChatHistoryMemoryProviderOptions
{
SearchInputMessageFilter = msgs => msgs,
StorageInputRequestMessageFilter = msgs => msgs,
});
this._contextPrompt = contextPrompt
?? "The following are memories from earlier in this conversation. Use them to inform your responses:";
}
/// <inheritdoc />
public override IReadOnlyList<string> StateKeys => this._stateKeys ??= this._chatHistoryProvider.StateKeys.Concat(this._memoryProvider.StateKeys).ToArray();
/// <inheritdoc />
protected override async ValueTask<IEnumerable<ChatMessage>> ProvideChatHistoryAsync(
InvokingContext context,
CancellationToken cancellationToken = default)
{
// Delegate to the inner provider's full lifecycle (retrieve, filter, stamp, merge with request messages).
var chatHistoryProviderInputContext = new InvokingContext(context.Agent, context.Session, []);
var allMessages = await this._chatHistoryProvider.InvokingAsync(chatHistoryProviderInputContext, cancellationToken).ConfigureAwait(false);
// Search the vector store for relevant older messages.
var aiContext = new AIContext { Messages = context.RequestMessages.ToList() };
var invokingContext = new AIContextProvider.InvokingContext(
context.Agent, context.Session, aiContext);
var result = await this._memoryProvider.InvokingAsync(invokingContext, cancellationToken).ConfigureAwait(false);
// Extract only the messages added by the memory provider (stamped with AIContextProvider source type).
var memoryMessages = result.Messages?
.Where(m => m.GetAgentRequestMessageSourceType() == AgentRequestMessageSourceType.AIContextProvider)
.ToList();
if (memoryMessages is { Count: > 0 })
{
var memoryText = string.Join("\n", memoryMessages.Select(m => m.Text).Where(t => !string.IsNullOrWhiteSpace(t)));
if (!string.IsNullOrWhiteSpace(memoryText))
{
var contextMessage = new ChatMessage(ChatRole.User, $"{this._contextPrompt}\n{memoryText}");
return new[] { contextMessage }.Concat(allMessages);
}
}
return allMessages;
}
/// <inheritdoc />
protected override async ValueTask StoreChatHistoryAsync(
InvokedContext context,
CancellationToken cancellationToken = default)
{
// Delegate storage to the in-memory provider. Its TruncatingChatReducer (AfterMessageAdded trigger)
// will automatically truncate to the configured maximum and expose any removed messages.
var innerContext = new InvokedContext(
context.Agent, context.Session, context.RequestMessages, context.ResponseMessages!);
await this._chatHistoryProvider.InvokedAsync(innerContext, cancellationToken).ConfigureAwait(false);
// Archive any messages that the reducer removed to the vector store.
if (this._reducer.RemovedMessages is { Count: > 0 })
{
var overflowContext = new AIContextProvider.InvokedContext(
context.Agent, context.Session, this._reducer.RemovedMessages, []);
await this._memoryProvider.InvokedAsync(overflowContext, cancellationToken).ConfigureAwait(false);
}
}
/// <inheritdoc/>
public void Dispose()
{
this._memoryProvider.Dispose();
}
}
@@ -1,79 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create a bounded chat history provider that keeps a configurable number of
// recent messages in session state and automatically overflows older messages to a vector store.
// When the agent is invoked, it searches the vector store for relevant older messages and
// prepends them as a "memory" context message before the recent session history.
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.InMemory;
using OpenAI.Chat;
using SampleApp;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
// 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.
var credential = new DefaultAzureCredential();
// Create a vector store to store overflow chat messages.
// For demonstration purposes, we are using an in-memory vector store.
// Replace this with a persistent vector store implementation for production scenarios.
VectorStore vectorStore = new InMemoryVectorStore(new InMemoryVectorStoreOptions()
{
EmbeddingGenerator = new AzureOpenAIClient(new Uri(endpoint), credential)
.GetEmbeddingClient(embeddingDeploymentName)
.AsIEmbeddingGenerator()
});
var sessionId = Guid.NewGuid().ToString();
// Create the BoundedChatHistoryProvider with a maximum of 4 non-system messages in session state.
// It internally creates an InMemoryChatHistoryProvider with a TruncatingChatReducer and a
// ChatHistoryMemoryProvider with the correct configuration to ensure overflow messages are
// automatically archived to the vector store and recalled via semantic search.
var boundedProvider = new BoundedChatHistoryProvider(
maxSessionMessages: 4,
vectorStore,
collectionName: "chathistory-overflow",
vectorDimensions: 3072,
session => new ChatHistoryMemoryProvider.State(
storageScope: new() { UserId = "UID1", SessionId = sessionId },
searchScope: new() { UserId = "UID1" }));
// Create the agent with the bounded chat history provider.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), credential)
.GetChatClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are a helpful assistant. Answer questions concisely." },
Name = "Assistant",
ChatHistoryProvider = boundedProvider,
});
// Start a conversation. The first several exchanges will fill up the session state window.
AgentSession session = await agent.CreateSessionAsync();
Console.WriteLine("--- Filling the session window (4 messages max) ---\n");
Console.WriteLine(await agent.RunAsync("My favorite color is blue.", session));
Console.WriteLine(await agent.RunAsync("I have a dog named Max.", session));
// At this point the session state holds 4 messages (2 user + 2 assistant).
// The next exchange will push the oldest messages into the vector store.
Console.WriteLine("\n--- Next exchange will trigger overflow to vector store ---\n");
Console.WriteLine(await agent.RunAsync("What is the capital of France?", session));
// The oldest messages about favorite color have now been archived to the vector store.
// Ask the agent something that requires recalling the overflowed information.
Console.WriteLine("\n--- Asking about overflowed information (should recall from vector store) ---\n");
Console.WriteLine(await agent.RunAsync("What is my favorite color?", session));
@@ -1,40 +0,0 @@
# Bounded Chat History with Vector Store Overflow
This sample demonstrates how to create a custom `ChatHistoryProvider` that keeps a bounded window of recent messages in session state and automatically overflows older messages to a vector store. When the agent is invoked, it searches the vector store for relevant older messages and prepends them as memory context.
## Concepts
- **`TruncatingChatReducer`**: A custom `IChatReducer` that keeps the most recent N messages and exposes removed messages via a `RemovedMessages` property.
- **`BoundedChatHistoryProvider`**: A custom `ChatHistoryProvider` that composes:
- `InMemoryChatHistoryProvider` for fast session-state storage (bounded by the reducer)
- `ChatHistoryMemoryProvider` for vector-store overflow and semantic search of older messages
## Prerequisites
- [.NET 10 SDK](https://dotnet.microsoft.com/download/dotnet/10.0)
- An Azure OpenAI resource with:
- A chat deployment (e.g., `gpt-4o-mini`)
- An embedding deployment (e.g., `text-embedding-3-large`)
## Configuration
Set the following environment variables:
| Variable | Description | Default |
|---|---|---|
| `AZURE_OPENAI_ENDPOINT` | Your Azure OpenAI endpoint URL | *(required)* |
| `AZURE_OPENAI_DEPLOYMENT_NAME` | Chat model deployment name | `gpt-4o-mini` |
| `AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME` | Embedding model deployment name | `text-embedding-3-large` |
## Running the Sample
```bash
dotnet run
```
## How it Works
1. The agent starts a conversation with a bounded session window of 4 non-system, non-function messages (i.e., user/assistant turns). System messages are always preserved, and function call/result messages are truncated and not preserved.
2. As messages accumulate beyond the limit, the `TruncatingChatReducer` removes the oldest messages.
3. The `BoundedChatHistoryProvider` detects the removed messages and stores them in a vector store via `ChatHistoryMemoryProvider`.
4. On subsequent invocations, the provider searches the vector store for relevant older messages and prepends them as memory context, allowing the agent to recall information from earlier in the conversation.
@@ -1,65 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
using Microsoft.Extensions.AI;
namespace SampleApp;
/// <summary>
/// A truncating chat reducer that keeps the most recent messages up to a configured maximum,
/// preserving any leading system message. Removed messages are exposed via <see cref="RemovedMessages"/>
/// so that a caller can archive them (e.g. to a vector store).
/// </summary>
internal sealed class TruncatingChatReducer : IChatReducer
{
private readonly int _maxMessages;
/// <summary>
/// Initializes a new instance of the <see cref="TruncatingChatReducer"/> class.
/// </summary>
/// <param name="maxMessages">The maximum number of non-system messages to retain.</param>
public TruncatingChatReducer(int maxMessages)
{
this._maxMessages = maxMessages > 0 ? maxMessages : throw new ArgumentOutOfRangeException(nameof(maxMessages));
}
/// <summary>
/// Gets the messages that were removed during the most recent call to <see cref="ReduceAsync"/>.
/// </summary>
public IReadOnlyList<ChatMessage> RemovedMessages { get; private set; } = [];
/// <inheritdoc />
public Task<IEnumerable<ChatMessage>> ReduceAsync(IEnumerable<ChatMessage> messages, CancellationToken cancellationToken)
{
_ = messages ?? throw new ArgumentNullException(nameof(messages));
ChatMessage? systemMessage = null;
Queue<ChatMessage> retained = new(capacity: this._maxMessages);
List<ChatMessage> removed = [];
foreach (var message in messages)
{
if (message.Role == ChatRole.System)
{
// Preserve the first system message outside the counting window.
systemMessage ??= message;
}
else if (!message.Contents.Any(c => c is FunctionCallContent or FunctionResultContent))
{
if (retained.Count >= this._maxMessages)
{
removed.Add(retained.Dequeue());
}
retained.Enqueue(message);
}
}
this.RemovedMessages = removed;
IEnumerable<ChatMessage> result = systemMessage is not null
? new[] { systemMessage }.Concat(retained)
: retained;
return Task.FromResult(result);
}
}
@@ -1,4 +1,4 @@
# Agent Framework Retrieval Augmented Generation (RAG)
# Agent Framework Retrieval Augmented Generation (RAG)
These samples show how to create an agent with the Agent Framework that uses Memory to remember previous conversations or facts from previous conversations.
@@ -8,6 +8,5 @@ These samples show how to create an agent with the Agent Framework that uses Mem
|[Memory with MemoryStore](./AgentWithMemory_Step02_MemoryUsingMem0/)|This sample demonstrates how to create and run an agent that uses the Mem0 service to extract and retrieve individual memories.|
|[Custom Memory Implementation](../../01-get-started/04_memory/)|This sample demonstrates how to create a custom memory component and attach it to an agent.|
|[Memory with Azure AI Foundry](./AgentWithMemory_Step04_MemoryUsingFoundry/)|This sample demonstrates how to create and run an agent that uses Azure AI Foundry's managed memory service to extract and retrieve individual memories.|
|[Bounded Chat History with Overflow](./AgentWithMemory_Step05_BoundedChatHistory/)|This sample demonstrates how to create a bounded chat history provider that overflows older messages to a vector store and recalls them as memories.|
> **See also**: [Memory Search with Foundry Agents](../AgentsWithFoundry/Agent_Step22_MemorySearch/) - demonstrates using the built-in Memory Search tool with Azure Foundry agents.
> **See also**: [Memory Search with Foundry Agents](../FoundryAgents/FoundryAgents_Step22_MemorySearch/) - demonstrates using the built-in Memory Search tool with Azure Foundry Agents.
@@ -4,14 +4,28 @@
using System.ClientModel;
using Microsoft.Agents.AI;
using OpenAI.Responses;
using OpenAI;
using OpenAI.Chat;
var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new InvalidOperationException("OPENAI_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt-4o-mini";
AIAgent agent =
new ResponsesClient(new ApiKeyCredential(apiKey))
.AsAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
AIAgent agent = new OpenAIClient(apiKey)
.GetChatClient(model)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
// Once you have the agent, you can invoke it like any other AIAgent.
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
UserChatMessage chatMessage = new("Tell me a joke about a pirate.");
// Invoke the agent and output the text result.
ChatCompletion chatCompletion = await agent.RunAsync([chatMessage]);
Console.WriteLine(chatCompletion.Content.Last().Text);
// Invoke the agent with streaming support.
AsyncCollectionResult<StreamingChatCompletionUpdate> completionUpdates = agent.RunStreamingAsync([chatMessage]);
await foreach (StreamingChatCompletionUpdate completionUpdate in completionUpdates)
{
if (completionUpdate.ContentUpdate.Count > 0)
{
Console.WriteLine(completionUpdate.ContentUpdate[0].Text);
}
}
@@ -10,8 +10,8 @@ var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new I
var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt-5";
var client = new OpenAIClient(apiKey)
.GetResponsesClient()
.AsIChatClient(model).AsBuilder()
.GetResponsesClient(model)
.AsIChatClient().AsBuilder()
.ConfigureOptions(o =>
{
o.Reasoning = new()
@@ -20,21 +20,19 @@ public class OpenAIResponseClientAgent : DelegatingAIAgent
/// <param name="instructions">Optional instructions for the agent.</param>
/// <param name="name">Optional name for the agent.</param>
/// <param name="description">Optional description for the agent.</param>
/// <param name="model">Optional default model ID to use for requests. Required when using a plain <see cref="ResponsesClient"/> (not via Azure OpenAI).</param>
/// <param name="loggerFactory">Optional instance of <see cref="ILoggerFactory"/></param>
public OpenAIResponseClientAgent(
ResponsesClient client,
string? instructions = null,
string? name = null,
string? description = null,
string? model = null,
ILoggerFactory? loggerFactory = null) :
this(client, new()
{
Name = name,
Description = description,
ChatOptions = new ChatOptions() { Instructions = instructions },
}, model, loggerFactory)
}, loggerFactory)
{
}
@@ -43,11 +41,10 @@ public class OpenAIResponseClientAgent : DelegatingAIAgent
/// </summary>
/// <param name="client">Instance of <see cref="ResponsesClient"/></param>
/// <param name="options">Options to create the agent.</param>
/// <param name="model">Optional default model ID to use for requests. Required when using a plain <see cref="ResponsesClient"/> (not via Azure OpenAI).</param>
/// <param name="loggerFactory">Optional instance of <see cref="ILoggerFactory"/></param>
public OpenAIResponseClientAgent(
ResponsesClient client, ChatClientAgentOptions options, string? model = null, ILoggerFactory? loggerFactory = null) :
base(new ChatClientAgent((client ?? throw new ArgumentNullException(nameof(client))).AsIChatClient(model), options, loggerFactory))
ResponsesClient client, ChatClientAgentOptions options, ILoggerFactory? loggerFactory = null) :
base(new ChatClientAgent((client ?? throw new ArgumentNullException(nameof(client))).AsIChatClient(), options, loggerFactory))
{
}
@@ -10,10 +10,10 @@ var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new I
var model = Environment.GetEnvironmentVariable("OPENAI_CHAT_MODEL_NAME") ?? "gpt-4o-mini";
// Create a ResponsesClient directly from OpenAIClient
ResponsesClient responseClient = new OpenAIClient(apiKey).GetResponsesClient();
ResponsesClient responseClient = new OpenAIClient(apiKey).GetResponsesClient(model);
// Create an agent directly from the ResponsesClient using OpenAIResponseClientAgent
OpenAIResponseClientAgent agent = new(responseClient, instructions: "You are good at telling jokes.", name: "Joker", model: model);
OpenAIResponseClientAgent agent = new(responseClient, instructions: "You are good at telling jokes.", name: "Joker");
ResponseItem userMessage = ResponseItem.CreateUserMessageItem("Tell me a joke about a pirate.");
@@ -22,7 +22,7 @@ OpenAIClient openAIClient = new(apiKey);
ConversationClient conversationClient = openAIClient.GetConversationClient();
// Create an agent directly from the ResponsesClient using OpenAIResponseClientAgent
ChatClientAgent agent = new(openAIClient.GetResponsesClient().AsIChatClient(model), instructions: "You are a helpful assistant.", name: "ConversationAgent");
ChatClientAgent agent = new(openAIClient.GetResponsesClient(model).AsIChatClient(), instructions: "You are a helpful assistant.", name: "ConversationAgent");
ClientResult createConversationResult = await conversationClient.CreateConversationAsync(BinaryContent.Create(BinaryData.FromString("{}")));
@@ -73,28 +73,16 @@ foreach (ClientResult result in getConversationItemsResults.GetRawPages())
using JsonDocument getConversationItemsResultAsJson = JsonDocument.Parse(result.GetRawResponse().Content.ToString());
foreach (JsonElement element in getConversationItemsResultAsJson.RootElement.GetProperty("data").EnumerateArray())
{
// Skip non-message items (e.g. tool calls, reasoning) that lack a "role" property
if (!element.TryGetProperty("role"u8, out var roleElement))
{
continue;
}
string messageId = element.GetProperty("id"u8).ToString();
string messageRole = roleElement.ToString();
string messageRole = element.GetProperty("role"u8).ToString();
Console.WriteLine($" Message ID: {messageId}");
Console.WriteLine($" Message Role: {messageRole}");
if (element.TryGetProperty("content"u8, out var contentElement))
foreach (var content in element.GetProperty("content").EnumerateArray())
{
foreach (var content in contentElement.EnumerateArray())
{
if (content.TryGetProperty("text"u8, out var textElement))
{
Console.WriteLine($" Message Text: {textElement}");
}
}
string messageContentText = content.GetProperty("text"u8).ToString();
Console.WriteLine($" Message Text: {messageContentText}");
}
Console.WriteLine();
}
}
@@ -4,13 +4,11 @@
using System.ClientModel;
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;
using Microsoft.Extensions.AI;
using OpenAI;
using OpenAI.Files;
using OpenAI.Responses;
using OpenAI.VectorStores;
var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
@@ -39,20 +37,14 @@ ClientResult<VectorStore> vectorStoreCreate = await vectorStoreClient.CreateVect
FileIds = { uploadResult.Value.Id }
});
// Use the native OpenAI SDK FileSearchTool directly with the vector store ID.
#pragma warning disable OPENAI001
FileSearchTool fileSearchTool = new([vectorStoreCreate.Value.Id]);
#pragma warning restore OPENAI001
var fileSearchTool = new HostedFileSearchTool() { Inputs = [new HostedVectorStoreContent(vectorStoreCreate.Value.Id)] };
AgentVersion agentVersion = await aiProjectClient.Agents.CreateAgentVersionAsync(
"AskContoso",
new AgentVersionCreationOptions(
new PromptAgentDefinition(model: deploymentName)
{
Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available.",
Tools = { fileSearchTool }
}));
FoundryAgent agent = aiProjectClient.AsAIAgent(agentVersion);
AIAgent agent = await aiProjectClient
.CreateAIAgentAsync(
model: deploymentName,
name: "AskContoso",
instructions: "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available.",
tools: [fileSearchTool]);
AgentSession session = await agent.CreateSessionAsync();
@@ -36,11 +36,11 @@ AIAgent agent = new AzureOpenAIClient(
// For simplicity, we are assuming here that only function approvals are pending.
AgentSession session = await agent.CreateSessionAsync();
AgentResponse response = await agent.RunAsync("What is the weather like in Amsterdam?", session);
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
// For streaming use:
// var updates = await agent.RunStreamingAsync("What is the weather like in Amsterdam?", session).ToListAsync();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<ToolApprovalRequestContent>().ToList();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<FunctionApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -48,18 +48,18 @@ while (approvalRequests.Count > 0)
List<ChatMessage> userInputResponses = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
// Pass the user input responses back to the agent for further processing.
response = await agent.RunAsync(userInputResponses, session);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
// For streaming use:
// updates = await agent.RunStreamingAsync(userInputResponses, session).ToListAsync();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<ToolApprovalRequestContent>().ToList();
// approvalRequests = updates.SelectMany(x => x.Contents).OfType<FunctionApprovalRequestContent>().ToList();
}
Console.WriteLine($"\nAgent: {response}");
@@ -10,14 +10,14 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.AI.Agents.Persistent" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
<PackageReference Include="ModelContextProtocol" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI\Microsoft.Agents.AI.AzureAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.AzureAI.Persistent\Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
</ItemGroup>
</Project>
@@ -2,8 +2,7 @@
// This sample shows how to expose an AI agent as an MCP tool.
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Azure.AI.Agents.Persistent;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.DependencyInjection;
@@ -16,20 +15,17 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYME
// 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.
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
var persistentAgentsClient = new PersistentAgentsClient(endpoint, new DefaultAzureCredential());
// Create a server side agent and expose it as an AIAgent.
AgentVersion agentVersion = await aiProjectClient.Agents.CreateAgentVersionAsync(
"Joker",
new AgentVersionCreationOptions(
new PromptAgentDefinition(model: deploymentName)
{
Instructions = "You are good at telling jokes, and you always start each joke with 'Aye aye, captain!'.",
})
{
Description = "An agent that tells jokes.",
});
AIAgent agent = aiProjectClient.AsAIAgent(agentVersion);
// Create a server side persistent agent
var agentMetadata = await persistentAgentsClient.Administration.CreateAgentAsync(
model: deploymentName,
instructions: "You are good at telling jokes, and you always start each joke with 'Aye aye, captain!'.",
name: "Joker",
description: "An agent that tells jokes.");
// Retrieve the server side persistent agent as an AIAgent.
AIAgent agent = await persistentAgentsClient.GetAIAgentAsync(agentMetadata.Value.Id);
// Convert the agent to an AIFunction and then to an MCP tool.
// The agent name and description will be used as the mcp tool name and description.
@@ -16,11 +16,5 @@
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
<ItemGroup>
<None Update="Assets\walkway.jpg">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
</ItemGroup>
</Project>
@@ -22,7 +22,7 @@ var agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential(
ChatMessage message = new(ChatRole.User, [
new TextContent("What do you see in this image?"),
await DataContent.LoadFromAsync("Assets/walkway.jpg"),
new UriContent("https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", "image/jpeg")
]);
var session = await agent.CreateSessionAsync();
@@ -25,9 +25,8 @@ var stateStore = new Dictionary<string, JsonElement?>();
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.GetResponsesClient(deploymentName)
.AsAIAgent(
model: deploymentName,
name: "SpaceNovelWriter",
instructions: "You are a space novel writer. Always research relevant facts and generate character profiles for the main characters before writing novels." +
"Write complete chapters without asking for approval or feedback. Do not ask the user about tone, style, pace, or format preferences - just write the novel based on the request.",
@@ -189,9 +189,9 @@ async Task<AgentResponse> PIIMiddleware(IEnumerable<ChatMessage> messages, Agent
// Regex patterns for PII detection (simplified for demonstration)
Regex[] piiPatterns =
[
MyRegex(), // Phone number (e.g., 123-456-7890)
EmailRegex(), // Email address
FullNameRegex() // Full name (e.g., John Doe)
new(@"\b\d{3}-\d{3}-\d{4}\b", RegexOptions.Compiled), // Phone number (e.g., 123-456-7890)
new(@"\b[\w\.-]+@[\w\.-]+\.\w+\b", RegexOptions.Compiled), // Email address
new(@"\b[A-Z][a-z]+\s[A-Z][a-z]+\b", RegexOptions.Compiled) // Full name (e.g., John Doe)
];
foreach (var pattern in piiPatterns)
@@ -246,7 +246,7 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
AgentResponse response = await innerAgent.RunAsync(messages, session, options, cancellationToken);
// For simplicity, we are assuming here that only function approvals are pending.
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
List<FunctionApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
while (approvalRequests.Count > 0)
{
@@ -255,13 +255,13 @@ async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMes
response.Messages = approvalRequests
.ConvertAll(functionApprovalRequest =>
{
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {functionApprovalRequest.FunctionCall.Name}");
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false)]);
});
response = await innerAgent.RunAsync(response.Messages, session, options, cancellationToken);
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<FunctionApprovalRequestContent>().ToList();
}
return response;
@@ -309,15 +309,3 @@ internal sealed class DateTimeContextProvider : MessageAIContextProvider
]);
}
}
internal partial class Program
{
[GeneratedRegex(@"\b\d{3}-\d{3}-\d{4}\b", RegexOptions.Compiled)]
private static partial Regex MyRegex();
[GeneratedRegex(@"\b[\w\.-]+@[\w\.-]+\.\w+\b", RegexOptions.Compiled)]
private static partial Regex EmailRegex();
[GeneratedRegex(@"\b[A-Z][a-z]+\s[A-Z][a-z]+\b", RegexOptions.Compiled)]
private static partial Regex FullNameRegex();
}
@@ -16,8 +16,8 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(model: deploymentName);
.GetResponsesClient(deploymentName)
.AsAIAgent();
// Enable background responses (only supported by OpenAI Responses at this time).
AgentRunOptions options = new() { AllowBackgroundResponses = true };
@@ -1,7 +1,5 @@
// Copyright (c) Microsoft. All rights reserved.
#pragma warning disable CS0618 // Type or member is obsolete - sample uses deprecated PersistentAgentsClientExtensions
// This sample shows how to create an Azure AI Foundry Agent with the Deep Research Tool.
using Azure.AI.Agents.Persistent;
@@ -17,10 +15,10 @@ var bingConnectionId = Environment.GetEnvironmentVariable("AZURE_AI_BING_CONNECT
PersistentAgentsAdministrationClientOptions persistentAgentsClientOptions = new();
persistentAgentsClientOptions.Retry.NetworkTimeout = TimeSpan.FromMinutes(20);
// Get a client to create/retrieve server side agents with.
// 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.
// Get a client to create/retrieve server side agents with.
PersistentAgentsClient persistentAgentsClient = new(endpoint, new DefaultAzureCredential(), persistentAgentsClientOptions);
// Define and configure the Deep Research tool.
@@ -23,14 +23,12 @@ Before running this sample, ensure you have:
Pay special attention to the purple `Note` boxes in the Azure documentation.
**Note**: The Bing Grounding Connection ID must be the **full ARM resource URI** from the project, not just the connection name. It has the following format:
**Note**: The Bing Connection ID must be from the **project**, not the resource. It has the following format:
```
/subscriptions/<sub-id>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<account>/projects/<project>/connections/<connection-name>
/subscriptions/<sub_id>/resourceGroups/<rg_name>/providers/<provider_name>/accounts/<account_name>/projects/<project_name>/connections/<connection_name>
```
You can find this in the Azure AI Foundry portal under **Management > Connected resources**, or retrieve it programmatically via the connections API (`.id` property).
## Environment Variables
Set the following environment variables:
@@ -39,8 +37,8 @@ Set the following environment variables:
# Replace with your Azure AI Foundry project endpoint
$env:AZURE_AI_PROJECT_ENDPOINT="https://your-project.services.ai.azure.com/"
# Replace with your Bing Grounding connection ID (full ARM resource URI)
$env:AZURE_AI_BING_CONNECTION_ID="/subscriptions/<sub-id>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<account>/projects/<project>/connections/<connection-name>"
# Replace with your Bing connection ID from the project
$env:AZURE_AI_BING_CONNECTION_ID="/subscriptions/.../connections/your-bing-connection"
# Optional, defaults to o3-deep-research
$env:AZURE_AI_REASONING_DEPLOYMENT_NAME="o3-deep-research"
@@ -12,9 +12,13 @@
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Agents.ObjectModel" />
<PackageReference Include="Microsoft.Agents.ObjectModel.Json" />
<PackageReference Include="Microsoft.Agents.ObjectModel.PowerFx" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Declarative\Microsoft.Agents.AI.Declarative.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
</ItemGroup>
@@ -24,12 +24,12 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
Func<Task<string[]>> loadNextThreeCalendarEvents = async () =>
{
// In a real implementation, this method would connect to a calendar service
return
[
return new string[]
{
"Doctor's appointment today at 15:00",
"Team meeting today at 17:00",
"Birthday party today at 20:00"
];
};
};
// Create an agent with an AI context provider attached that aggregates two other providers:
@@ -87,7 +87,7 @@ namespace SampleApp
internal sealed class TodoListAIContextProvider : AIContextProvider
{
private static List<string> GetTodoItems(AgentSession? session)
=> session?.StateBag.GetValue<List<string>>(nameof(TodoListAIContextProvider)) ?? [];
=> session?.StateBag.GetValue<List<string>>(nameof(TodoListAIContextProvider)) ?? new List<string>();
private static void SetTodoItems(AgentSession? session, List<string> items)
=> session?.StateBag.SetValue(nameof(TodoListAIContextProvider), items);
@@ -1,120 +0,0 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use a CompactionProvider with a compaction pipeline
// as an AIContextProvider for an agent's in-run context management. The pipeline chains multiple
// compaction strategies from gentle to aggressive:
// 1. ToolResultCompactionStrategy - Collapses old tool-call groups into concise summaries
// 2. SummarizationCompactionStrategy - LLM-compresses older conversation spans
// 3. SlidingWindowCompactionStrategy - Keeps only the most recent N user turns
// 4. TruncationCompactionStrategy - Emergency token-budget backstop
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Compaction;
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-4o-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create a chat client for the agent and a separate one for the summarization strategy.
// Using the same model for simplicity; in production, use a smaller/cheaper model for summarization.
IChatClient agentChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
IChatClient summarizerChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
// Define a tool the agent can use, so we can see tool-result compaction in action.
[Description("Look up the current price of a product by name.")]
static string LookupPrice([Description("The product name to look up.")] string productName) =>
productName.ToUpperInvariant() switch
{
"LAPTOP" => "The laptop costs $999.99.",
"KEYBOARD" => "The keyboard costs $79.99.",
"MOUSE" => "The mouse costs $29.99.",
_ => $"Sorry, I don't have pricing for '{productName}'."
};
// Configure the compaction pipeline with one of each strategy, ordered least to most aggressive.
PipelineCompactionStrategy compactionPipeline =
new(// 1. Gentle: collapse old tool-call groups into short summaries
new ToolResultCompactionStrategy(CompactionTriggers.MessagesExceed(7)),
// 2. Moderate: use an LLM to summarize older conversation spans into a concise message
new SummarizationCompactionStrategy(summarizerChatClient, CompactionTriggers.TokensExceed(0x500)),
// 3. Aggressive: keep only the last N user turns and their responses
new SlidingWindowCompactionStrategy(CompactionTriggers.TurnsExceed(4)),
// 4. Emergency: drop oldest groups until under the token budget
new TruncationCompactionStrategy(CompactionTriggers.TokensExceed(0x8000)));
// Create the agent with a CompactionProvider that uses the compaction pipeline.
AIAgent agent =
agentChatClient
.AsBuilder()
// Note: Adding the CompactionProvider at the builder level means it will be applied to all agents
// built from this builder and will manage context for both agent messages and tool calls.
.UseAIContextProviders(new CompactionProvider(compactionPipeline))
.BuildAIAgent(
new ChatClientAgentOptions
{
Name = "ShoppingAssistant",
ChatOptions = new()
{
Instructions =
"""
You are a helpful, but long winded, shopping assistant.
Help the user look up prices and compare products.
When responding, Be sure to be extra descriptive and use as
many words as possible without sounding ridiculous.
""",
Tools = [AIFunctionFactory.Create(LookupPrice)]
},
// Note: AIContextProviders may be specified here instead of ChatClientBuilder.UseAIContextProviders.
// Specifying compaction at the agent level skips compaction in the function calling loop.
//AIContextProviders = [new CompactionProvider(compactionPipeline)]
});
AgentSession session = await agent.CreateSessionAsync();
// Helper to print chat history size
void PrintChatHistory()
{
if (session.TryGetInMemoryChatHistory(out var history))
{
Console.ForegroundColor = ConsoleColor.Cyan;
Console.WriteLine($"\n[Messages: #{history.Count}]\n");
Console.ResetColor();
}
}
// Run a multi-turn conversation with tool calls to exercise the pipeline.
string[] prompts =
[
"What's the price of a laptop?",
"How about a keyboard?",
"And a mouse?",
"Which product is the cheapest?",
"Can you compare the laptop and the keyboard for me?",
"What was the first product I asked about?",
"Thank you!",
];
foreach (string prompt in prompts)
{
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[User] ");
Console.ResetColor();
Console.WriteLine(prompt);
Console.ForegroundColor = ConsoleColor.Cyan;
Console.Write("\n[Agent] ");
Console.ResetColor();
Console.WriteLine(await agent.RunAsync(prompt, session));
PrintChatHistory();
}

Some files were not shown because too many files have changed in this diff Show More