Files
agent-framework/dotnet/samples/04-hosting/FoundryHostedAgents/responses/Hosted-AgentSkills/Program.cs
T
dc4bafbc1e .NET: Add Hosted-AgentSkills sample with Foundry Skills integration (#6013)
* .NET: Add Hosted-AgentSkills sample for Foundry Skills integration

Add a new hosted agent sample that demonstrates how to load behavioral
guidelines from Foundry Skills at startup using AgentSkillsProvider and
the progressive disclosure pattern (advertise -> load on demand).

The sample:
- Downloads SKILL.md files from Foundry via ProjectAgentSkills SDK
- Extracts ZIP archives with zip-slip protection
- Wires skills into AgentSkillsProvider as an AIContextProvider
- Hosts the agent via the Responses protocol

Ships two Contoso Outdoors skills matching the Python sample (PR #5822):
- support-style: tone, formatting, signature guidelines
- escalation-policy: when and how to escalate tickets

Includes convenience provisioning gated behind PROVISION_SAMPLE_SKILLS
env var, clearly documented as NOT a production pattern.

Closes #5776

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: Add unit tests and integration test for Hosted-AgentSkills

Unit tests (14 tests, all passing):
- ZIP extraction with zip-slip guard (valid archive, traversal attack,
  sibling-prefix attack, directory entries)
- Skill name validation (rejects dots, separators, traversal patterns)
- AgentSkillsProvider with downloaded skills (advertises both skills,
  load_skill returns canary tokens, unknown skill returns error)

Container integration test:
- New 'agent-skills' scenario in the test container that creates
  Contoso Outdoors skills on disk and wires AgentSkillsProvider
- AgentSkillsHostedAgentFixture + 4 integration tests verifying:
  - Routine questions load support-style skill (STYLE-CANARY-3318)
  - Escalation triggers load escalation-policy (ESC-CANARY-7742)
  - Skills are advertised in system prompt
  - load_skill tool is invoked via FunctionCallContent

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: Add smoke test, bootstrap, and docs for agent-skills integration

- Add scripts/smoke.ps1 for local Docker smoke testing: builds the
  contributor image, runs the container, verifies both skills are loaded
  via canary tokens (STYLE-CANARY-3318, ESC-CANARY-7742)
- Add 'agent-skills' to the bootstrap script scenario list
- Add agent-skills row to the integration test README scenarios table
- Exclude HostedAgentSkillsPatternTests from net472 (uses net8.0+ APIs)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: Update commented-out package versions to latest across all hosted samples

Update the end-user PackageReference versions (in the commented-out
sections) from 1.0.0 to the current latest NuGet versions:

- Microsoft.Agents.AI: 1.6.1
- Microsoft.Agents.AI.Foundry: 1.6.1-preview.260514.1
- Microsoft.Agents.AI.Foundry.Hosting: 1.6.1-preview.260514.1
- Microsoft.Agents.AI.Hosting: 1.6.1-preview.260514.1
- Microsoft.Agents.AI.OpenAI: 1.6.1
- Microsoft.Agents.AI.Workflows: 1.6.1

Also adds explicit versions to Hosted-Workflow-Handoff which had bare
PackageReference entries without Version attributes.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: Fix broken markdown links in Hosted-AgentSkills README

Remove references to non-existent ../../README.md. Replace with
inline instructions matching other hosted samples that don't have
a parent README.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* .NET: Use OS-appropriate string comparison in zip-slip guard

Use Ordinal on Unix (case-sensitive FS) and OrdinalIgnoreCase on
Windows to prevent case-based path bypass on Linux containers.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-05-25 09:32:04 +00:00

216 lines
9.8 KiB
C#

// Copyright (c) Microsoft. All rights reserved.
// Hosted-AgentSkills
//
// Demonstrates how to host an agent that loads its behavioral guidelines from Foundry Skills at
// startup. Skills are authored as SKILL.md files, uploaded to Foundry via the Skills REST API,
// and downloaded by the agent on boot so guideline updates ship without code changes.
//
// The agent uses AgentSkillsProvider from the Agent Framework which implements the progressive
// disclosure pattern from the Agent Skills specification (https://agentskills.io/):
// 1. Advertise — skill names and descriptions are injected into the system prompt.
// 2. Load — the model calls load_skill to retrieve the full SKILL.md body on demand.
//
// IMPORTANT: In production, skill provisioning (uploading SKILL.md files to Foundry) is an
// external concern — it is NOT the hosted agent's responsibility. The provisioning helper below
// is included for sample convenience only, so the sample is self-contained and runnable without
// a separate setup step. A real deployment pipeline would provision skills separately (e.g., via
// a CI/CD step, a CLI script, or a management portal).
#pragma warning disable AAIP001 // ProjectAgentSkills is experimental
using System.ClientModel;
using System.IO.Compression;
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Azure.Core;
using Azure.Identity;
using DotNetEnv;
using Hosted_Shared_Contributor_Setup;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Foundry.Hosting;
using Microsoft.Extensions.AI;
// Load .env file if present (for local development)
Env.TraversePath().Load();
string endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT")
?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-4o";
string skillNames = Environment.GetEnvironmentVariable("SKILL_NAMES")
?? throw new InvalidOperationException("SKILL_NAMES is not set. Provide a comma-separated list of skill names (e.g., support-style,escalation-policy).");
string[] requestedSkills = skillNames.Split(',', StringSplitOptions.RemoveEmptyEntries | StringSplitOptions.TrimEntries);
if (requestedSkills.Length == 0)
{
throw new InvalidOperationException("SKILL_NAMES must list at least one skill name.");
}
// Validate skill names to prevent path traversal.
foreach (string name in requestedSkills)
{
if (name.Contains('.') || name.Contains('/') || name.Contains('\\') || Path.IsPathRooted(name))
{
throw new InvalidOperationException(
$"Invalid skill name '{name}': skill names must not contain path separators or dots.");
}
}
// Use a chained credential: try a temporary dev token first (for local Docker debugging),
// then fall back to DefaultAzureCredential (for local dev via dotnet run / managed identity in production).
TokenCredential credential = new ChainedTokenCredential(
new DevTemporaryTokenCredential(),
new DefaultAzureCredential());
AIProjectClient projectClient = new(new Uri(endpoint), credential);
ProjectAgentSkills skillsClient = projectClient.AgentAdministrationClient.GetAgentSkills();
// ── Provision skills (sample convenience only — NOT a production pattern) ─────
// In production, skills are provisioned externally (e.g., via CI/CD or a management script).
// This helper ensures the sample's SKILL.md files exist in Foundry so the sample is runnable
// out of the box without a separate setup step. Set PROVISION_SAMPLE_SKILLS=true to enable.
string sourceSkillsDir = Path.Combine(AppContext.BaseDirectory, "skills");
bool provisionEnabled = string.Equals(
Environment.GetEnvironmentVariable("PROVISION_SAMPLE_SKILLS"), "true", StringComparison.OrdinalIgnoreCase);
if (provisionEnabled && Directory.Exists(sourceSkillsDir))
{
await EnsureSkillsProvisionedAsync(skillsClient, sourceSkillsDir, requestedSkills);
}
// ── Download skills from Foundry ─────────────────────────────────────────────
// Pull the latest copy of each skill from Foundry into a runtime-only folder.
// This directory is recreated on every startup so the agent always picks up
// the latest version of each skill.
string downloadedSkillsDir = Path.Combine(AppContext.BaseDirectory, "downloaded_skills");
await DownloadSkillsAsync(skillsClient, requestedSkills, downloadedSkillsDir);
// ── Wire skills into the agent ───────────────────────────────────────────────
// AgentSkillsProvider implements progressive disclosure: skill names and descriptions
// are advertised in the system prompt (~100 tokens per skill), and the full SKILL.md
// body is loaded on demand when the model calls the load_skill tool.
AgentSkillsProvider skillsProvider = new(downloadedSkillsDir);
ChatClientAgent agent = projectClient.AsAIAgent(new ChatClientAgentOptions
{
Name = Environment.GetEnvironmentVariable("AGENT_NAME") ?? "hosted-agent-skills",
ChatOptions = new ChatOptions
{
ModelId = deploymentName,
Instructions = "You are a customer-support assistant for Contoso Outdoors.",
},
AIContextProviders = [skillsProvider]
});
// Host the agent as a Foundry Hosted Agent using the Responses API.
var builder = WebApplication.CreateBuilder(args);
builder.Services.AddFoundryResponses(agent);
builder.Services.AddDevTemporaryLocalContributorSetup(); // Local Docker debugging only - must not be used in production.
var app = builder.Build();
app.MapFoundryResponses();
// Contributor-only: in Development, also map the per-agent OpenAI route shape that live Foundry uses
// so a local REPL client can target this server via AIProjectClient.AsAIAgent(Uri agentEndpoint).
// Do not use this in production. Hosted Foundry agents only support the agent-endpoint path.
app.MapDevTemporaryLocalAgentEndpoint();
app.Run();
// ── Helpers ──────────────────────────────────────────────────────────────────
// Downloads each named skill from Foundry and extracts the ZIP archive into a
// separate subdirectory under the target directory.
static async Task DownloadSkillsAsync(ProjectAgentSkills skillsClient, string[] skillNames, string targetDir)
{
if (Directory.Exists(targetDir))
{
Directory.Delete(targetDir, recursive: true);
}
Directory.CreateDirectory(targetDir);
foreach (string name in skillNames)
{
Console.WriteLine($"Downloading skill '{name}' from Foundry...");
BinaryData zipData = await skillsClient.DownloadSkillAsync(name);
string skillDir = Path.Combine(targetDir, name);
Directory.CreateDirectory(skillDir);
using var zipStream = zipData.ToStream();
using var archive = new ZipArchive(zipStream, ZipArchiveMode.Read);
SafeExtractZip(archive, skillDir);
if (!File.Exists(Path.Combine(skillDir, "SKILL.md")))
{
throw new InvalidOperationException(
$"Downloaded archive for '{name}' did not contain a SKILL.md at the root.");
}
}
}
// Extracts a ZIP archive into a destination directory, rejecting entries that would
// escape the target path (zip-slip guard).
static void SafeExtractZip(ZipArchive archive, string destinationDir)
{
string destRoot = Path.GetFullPath(destinationDir);
string destRootWithSep = Path.EndsInDirectorySeparator(destRoot)
? destRoot
: destRoot + Path.DirectorySeparatorChar;
// Use ordinal comparison on Unix (case-sensitive FS) and ordinal-ignore-case on Windows.
var comparison = OperatingSystem.IsWindows()
? StringComparison.OrdinalIgnoreCase
: StringComparison.Ordinal;
foreach (ZipArchiveEntry entry in archive.Entries)
{
string entryPath = Path.GetFullPath(Path.Combine(destRoot, entry.FullName));
if (!entryPath.StartsWith(destRootWithSep, comparison)
&& !string.Equals(entryPath, destRoot, comparison))
{
throw new InvalidOperationException(
$"Refusing to extract unsafe path '{entry.FullName}' outside of '{destRoot}'.");
}
if (string.IsNullOrEmpty(entry.Name))
{
// Directory entry — ensure it exists.
Directory.CreateDirectory(entryPath);
}
else
{
Directory.CreateDirectory(Path.GetDirectoryName(entryPath)!);
entry.ExtractToFile(entryPath, overwrite: true);
}
}
}
// Ensures each requested skill is provisioned in Foundry. For each skill name, checks whether
// the skill exists and uploads it from the local source directory if it does not.
//
// This is a sample convenience helper — in production, skill provisioning is an external concern.
static async Task EnsureSkillsProvisionedAsync(ProjectAgentSkills skillsClient, string sourceDir, string[] skillNames)
{
foreach (string name in skillNames)
{
string skillPath = Path.Combine(sourceDir, name);
if (!Directory.Exists(skillPath) || !File.Exists(Path.Combine(skillPath, "SKILL.md")))
{
continue; // No local source for this skill — skip provisioning.
}
try
{
await skillsClient.GetSkillAsync(name);
Console.WriteLine($"Skill '{name}' already exists in Foundry.");
}
catch (ClientResultException ex) when (ex.Status == 404)
{
Console.WriteLine($"Provisioning skill '{name}' from {skillPath}...");
AgentsSkill imported = await skillsClient.CreateSkillFromPackageAsync(skillPath);
Console.WriteLine($" Imported skill '{imported.Name}' (id={imported.SkillId}, has_blob={imported.HasBlob}).");
}
}
}