Comments

README.md

@@ -94,23 +94,23 @@ Create a simple Azure Responses Agent that writes a haiku about the Microsoft Ag
 # Use `az login` to authenticate with Azure CLI
 import os
 import asyncio
-from agent_framework import Agent
-from agent_framework.foundry import FoundryChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 
 
 async def main():
-    # Initialize a chat agent with Microsoft Foundry
+    # Initialize a chat agent with Azure OpenAI Responses
     # the endpoint, deployment name, and api version can be set via environment variables
-    # or they can be passed in directly to the FoundryChatClient constructor
-    agent = Agent(
-      client=FoundryChatClient(
-          credential=AzureCliCredential(),
-          # project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-          # model=os.environ["FOUNDRY_MODEL_DEPLOYMENT_NAME"],
-      ),
-      name="HaikuBot",
-      instructions="You are an upbeat assistant that writes beautifully.",
+    # or they can be passed in directly to the AzureOpenAIResponsesClient constructor
+    agent = AzureOpenAIResponsesClient(
+        # endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
+        # deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+        # api_version=os.environ["AZURE_OPENAI_API_VERSION"],
+        # api_key=os.environ["AZURE_OPENAI_API_KEY"],  # Optional if using AzureCliCredential
+        credential=AzureCliCredential(), # Optional, if using api_key
+    ).as_agent(
+        name="HaikuBot",
+        instructions="You are an upbeat assistant that writes beautifully.",
     )
 
     print(await agent.run("Write a haiku about Microsoft Agent Framework."))

dotnet/.github/skills/verify-samples-tool/SKILL.md

@@ -1,213 +0,0 @@
----
-name: verify-samples-tool
-description: How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
----
-
-# verify-samples Tool
-
-The `verify-samples` project (`dotnet/eng/verify-samples/`) is an automated tool that runs sample projects and verifies their output using deterministic checks and AI-powered verification.
-
-## Running verify-samples
-
-```bash
-cd dotnet
-
-# Run all samples across all categories
-dotnet run --project eng/verify-samples -- --log results.log --csv results.csv
-
-# Run a specific category
-dotnet run --project eng/verify-samples -- --category 02-agents --log results.log
-
-# Run specific samples by name
-dotnet run --project eng/verify-samples -- Agent_Step02_StructuredOutput Agent_Step09_AsFunctionTool
-
-# Control parallelism (default 8)
-dotnet run --project eng/verify-samples -- --parallel 8 --log results.log
-
-# Combine options
-dotnet run --project eng/verify-samples -- --category 03-workflows --parallel 4 --log results.log --csv results.csv
-```
-
-### Required Environment Variables
-
-The tool itself needs:
-- `AZURE_OPENAI_ENDPOINT` — for the AI verification agent
-- `AZURE_OPENAI_DEPLOYMENT_NAME` (optional, defaults to `gpt-5-mini`)
-
-Individual samples require their own env vars (e.g., `AZURE_AI_PROJECT_ENDPOINT`). The tool automatically checks and skips samples with missing env vars.
-
-### Output Files
-
-- `--log results.log` — detailed per-sample log with stdout/stderr, AI reasoning, and a summary
-- `--csv results.csv` — tabular summary with Sample, ProjectPath, Status, FailedChecks, and Failures columns
-
-## Sample Categories
-
-Definitions are in the `dotnet/eng/verify-samples/` directory:
-
-| Category | Config File | Registered Key |
-|----------|-------------|----------------|
-| 01-get-started | `GetStartedSamples.cs` | `01-get-started` |
-| 02-agents | `AgentsSamples.cs` | `02-agents` |
-| 03-workflows | `WorkflowSamples.cs` | `03-workflows` |
-
-Categories are registered in `VerifyOptions.cs` in the `s_sampleSets` dictionary.
-
-## SampleDefinition Properties
-
-Each sample is defined as a `SampleDefinition` in the appropriate config file. Key properties:
-
-```csharp
-new SampleDefinition
-{
-    // Required: Display name for the sample
-    Name = "Agent_Step02_StructuredOutput",
-
-    // Required: Relative path from dotnet/ to the sample project directory
-    ProjectPath = "samples/02-agents/Agents/Agent_Step02_StructuredOutput",
-
-    // Environment variables the sample requires (throws if missing)
-    RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-
-    // Environment variables with defaults that would prompt on console if unset
-    OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-
-    // Skip this sample with a reason (for structural issues only)
-    SkipReason = null, // or "Requires external service X."
-
-    // Deterministic checks: substrings that must appear in stdout
-    MustContain = ["=== Section Header ==="],
-
-    // Substrings that must NOT appear in stdout
-    MustNotContain = [],
-
-    // If true, only MustContain checks are used (no AI verification)
-    IsDeterministic = false,
-
-    // AI verification: natural-language descriptions of expected output
-    // Each entry describes one aspect to verify independently
-    ExpectedOutputDescription =
-    [
-        "The output should show structured person information with Name, Age, and Occupation fields.",
-        "The output should not contain error messages or stack traces.",
-    ],
-
-    // Stdin inputs to feed to the sample (for interactive samples)
-    Inputs = ["Y", "Y", "Y"],
-
-    // Delay between stdin inputs in ms (default 2000, increase for LLM calls between inputs)
-    InputDelayMs = 3000,
-}
-```
-
-## How to Add a New Sample Definition
-
-1. **Check the sample's Program.cs** to understand:
-   - What environment variables it reads (look for `GetEnvironmentVariable`)
-   - Whether it needs stdin input (look for `Console.ReadLine`, `Application.GetInput`)
-   - Whether it has an external loop (look for `EXIT` patterns in YAML workflows)
-   - What output it produces (section headers, markers, expected behavior)
-   - Whether it exits on its own or runs as a server
-
-2. **Choose the right verification strategy:**
-   - **Deterministic** (`IsDeterministic = true`): Use `MustContain` for samples with fixed output strings. No AI verification.
-   - **AI-verified** (default): Use `ExpectedOutputDescription` with semantic descriptions. Write expectations that are flexible enough for non-deterministic LLM output.
-   - **Both**: Use `MustContain` for fixed markers AND `ExpectedOutputDescription` for LLM-generated content.
-
-3. **Set `SkipReason` only for structural issues:**
-   - Web servers that don't exit
-   - Multi-process client/server architectures
-   - Samples requiring external infrastructure (MCP servers you can't reach, Docker, etc.)
-   - Do NOT skip for missing env vars — the tool checks those dynamically.
-
-4. **For interactive samples, provide `Inputs`:**
-   - Samples using `Application.GetInput(args)` need one initial input
-   - Samples with `Console.ReadLine()` approval loops need `"Y"` inputs
-   - YAML workflows with `externalLoop` need `"EXIT"` as the last input
-   - Set `InputDelayMs` to 3000-8000ms for samples with LLM calls between inputs
-
-5. **Add the definition** to the appropriate config file (e.g., `AgentsSamples.cs`) in the `All` list.
-
-6. **Register new categories** (if needed) in `VerifyOptions.cs` `s_sampleSets` dictionary.
-
-### Writing Good ExpectedOutputDescription
-
-- Write descriptions that are **semantically flexible** — LLM output varies between runs
-- Each array entry should describe **one independent aspect** to verify
-- Always include `"The output should not contain error messages or stack traces."` as the last entry
-- Avoid exact wording expectations — use "should mention", "should contain information about", "should show"
-- Bad: `"The output should say 'The weather in Amsterdam is cloudy with a high of 15°C'"`
-- Good: `"The output should contain weather information about Amsterdam mentioning cloudy weather with a high of 15°C."`
-
-### Example: Simple LLM Sample
-
-```csharp
-new SampleDefinition
-{
-    Name = "Agent_With_AzureOpenAIChatCompletion",
-    ProjectPath = "samples/02-agents/AgentProviders/Agent_With_AzureOpenAIChatCompletion",
-    RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-    OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-    ExpectedOutputDescription =
-    [
-        "The output should contain a joke about a pirate.",
-        "The output should not contain error messages or stack traces.",
-    ],
-},
-```
-
-### Example: Deterministic Sample
-
-```csharp
-new SampleDefinition
-{
-    Name = "Workflow_Declarative_GenerateCode",
-    ProjectPath = "samples/03-workflows/Declarative/GenerateCode",
-    IsDeterministic = true,
-    MustContain = ["WORKFLOW: Parsing", "WORKFLOW: Defined"],
-    ExpectedOutputDescription = ["The output should show a YAML workflow being parsed and C# code being generated from it."],
-},
-```
-
-### Example: Interactive Sample with Approval Loop
-
-```csharp
-new SampleDefinition
-{
-    Name = "FoundryAgent_Hosted_MCP",
-    ProjectPath = "samples/02-agents/ModelContextProtocol/FoundryAgent_Hosted_MCP",
-    RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-    OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-    Inputs = ["Y", "Y", "Y", "Y", "Y"],
-    InputDelayMs = 5000,
-    ExpectedOutputDescription = ["The output should show an agent using the Microsoft Learn MCP tool with approval prompts."],
-},
-```
-
-### Example: Declarative Workflow with External Loop
-
-```csharp
-new SampleDefinition
-{
-    Name = "Workflow_Declarative_FunctionTools",
-    ProjectPath = "samples/03-workflows/Declarative/FunctionTools",
-    RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-    OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-    Inputs = ["What are today's specials?", "EXIT"],
-    InputDelayMs = 8000,
-    ExpectedOutputDescription = ["The output should show a workflow calling function tools to answer a question about restaurant specials."],
-},
-```
-
-### Example: Skipped Sample
-
-```csharp
-new SampleDefinition
-{
-    Name = "Agent_MCP_Server",
-    ProjectPath = "samples/02-agents/ModelContextProtocol/Agent_MCP_Server",
-    RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-    OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-    SkipReason = "Runs as an MCP stdio server that does not exit on its own.",
-},
-```

dotnet/agent-framework-dotnet.slnx

@@ -7,7 +7,6 @@
   <Folder Name="/Samples/">
     <File Path="samples/AGENTS.md" />
     <File Path="samples/README.md" />
-    <Project Path="eng/verify-samples/verify-samples.csproj" />
   </Folder>
   <Folder Name="/Samples/01-get-started/">
     <Project Path="samples/01-get-started/01_hello_agent/01_hello_agent.csproj" />
@@ -172,7 +171,6 @@
     <Project Path="samples/02-agents/AgentWithRAG/AgentWithRAG_Step02_CustomVectorStoreRAG/AgentWithRAG_Step02_CustomVectorStoreRAG.csproj" />
     <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" />
-    <Project Path="samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/AgentWithRAG_Step05_Neo4jGraphRAG.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/ModelContextProtocol/">
     <File Path="samples/02-agents/ModelContextProtocol/README.md" />

dotnet/eng/verify-samples/ConsoleReporter.cs

@@ -1,95 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// Thread-safe console output with sample-name prefixes and colored status.
-/// </summary>
-internal sealed class ConsoleReporter
-{
-    private readonly object _lock = new();
-
-    /// <summary>
-    /// Writes a complete prefixed line atomically to the console.
-    /// </summary>
-    public void WriteLineWithPrefix(string sampleName, string message, ConsoleColor? color = null)
-    {
-        lock (this._lock)
-        {
-            Console.ForegroundColor = ConsoleColor.Cyan;
-            Console.Write($"[{sampleName}] ");
-            if (color.HasValue)
-            {
-                Console.ForegroundColor = color.Value;
-            }
-            else
-            {
-                Console.ResetColor();
-            }
-
-            Console.WriteLine(message);
-            Console.ResetColor();
-        }
-    }
-
-    /// <summary>
-    /// Prints the final summary table and elapsed time to the console.
-    /// </summary>
-    public void PrintSummary(
-        IReadOnlyList<VerificationResult> orderedResults,
-        IReadOnlyList<(string Name, string Reason)> skipped,
-        TimeSpan elapsed)
-    {
-        var passCount = orderedResults.Count(r => r.Passed);
-        var failCount = orderedResults.Count(r => !r.Passed);
-
-        Console.WriteLine();
-        Console.WriteLine(new string('─', 60));
-        Console.ForegroundColor = ConsoleColor.White;
-        Console.WriteLine("SUMMARY");
-        Console.ResetColor();
-
-        foreach (var result in orderedResults)
-        {
-            Console.ForegroundColor = result.Passed ? ConsoleColor.Green : ConsoleColor.Red;
-            Console.Write(result.Passed ? "  ✓ " : "  ✗ ");
-            Console.ResetColor();
-            Console.WriteLine($"{result.SampleName}: {result.Summary}");
-        }
-
-        foreach (var (name, reason) in skipped)
-        {
-            Console.ForegroundColor = ConsoleColor.Yellow;
-            Console.Write("  ○ ");
-            Console.ResetColor();
-            Console.WriteLine($"{name}: Skipped — {reason}");
-        }
-
-        Console.WriteLine();
-        Console.Write("Results: ");
-        Console.ForegroundColor = ConsoleColor.Green;
-        Console.Write($"{passCount} passed");
-        Console.ResetColor();
-
-        if (failCount > 0)
-        {
-            Console.Write(", ");
-            Console.ForegroundColor = ConsoleColor.Red;
-            Console.Write($"{failCount} failed");
-            Console.ResetColor();
-        }
-
-        if (skipped.Count > 0)
-        {
-            Console.Write(", ");
-            Console.ForegroundColor = ConsoleColor.Yellow;
-            Console.Write($"{skipped.Count} skipped");
-            Console.ResetColor();
-        }
-
-        Console.WriteLine();
-        Console.ForegroundColor = ConsoleColor.DarkGray;
-        Console.WriteLine($"Elapsed: {elapsed.Hours:D2}:{elapsed.Minutes:D2}:{elapsed.Seconds:D2}");
-        Console.ResetColor();
-    }
-}

dotnet/eng/verify-samples/CsvResultWriter.cs

@@ -1,56 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Text;
-
-namespace VerifySamples;
-
-/// <summary>
-/// Writes a CSV summary of sample verification results.
-/// </summary>
-internal static class CsvResultWriter
-{
-    /// <summary>
-    /// Writes the results to a CSV file at the specified path.
-    /// </summary>
-    public static async Task WriteAsync(
-        string path,
-        IReadOnlyList<VerificationResult> orderedResults,
-        IReadOnlyList<(string Name, string Reason)> skipped,
-        IReadOnlyList<SampleDefinition> samples)
-    {
-        var pathLookup = samples.ToDictionary(s => s.Name, s => s.ProjectPath);
-
-        var sb = new StringBuilder();
-        sb.AppendLine("Sample,ProjectPath,Status,FailedChecks,Failures");
-
-        foreach (var result in orderedResults)
-        {
-            var status = result.Passed ? "PASSED" : "FAILED";
-            var failedChecks = result.Failures.Count;
-            var failures = string.Join("; ", result.Failures);
-            pathLookup.TryGetValue(result.SampleName, out var projectPath);
-            sb.AppendLine($"{CsvEscape(result.SampleName)},{CsvEscape(projectPath ?? "")},{status},{failedChecks},{CsvEscape(failures)}");
-        }
-
-        foreach (var (name, reason) in skipped)
-        {
-            pathLookup.TryGetValue(name, out var projectPath);
-            sb.AppendLine($"{CsvEscape(name)},{CsvEscape(projectPath ?? "")},SKIPPED,0,{CsvEscape(reason)}");
-        }
-
-        await File.WriteAllTextAsync(path, sb.ToString());
-    }
-
-    /// <summary>
-    /// Escapes a value for CSV: wraps in quotes if it contains commas, quotes, or newlines.
-    /// </summary>
-    private static string CsvEscape(string value)
-    {
-        if (value.Contains('"') || value.Contains(',') || value.Contains('\n') || value.Contains('\r'))
-        {
-            return $"\"{value.Replace("\"", "\"\"")}\"";
-        }
-
-        return value;
-    }
-}

dotnet/eng/verify-samples/GetStartedSamples.cs

@@ -1,105 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// Defines the expected behavior for each sample in 01-get-started.
-/// </summary>
-internal static class GetStartedSamples
-{
-    public static IReadOnlyList<SampleDefinition> All { get; } =
-    [
-        new SampleDefinition
-        {
-            Name = "05_first_workflow",
-            ProjectPath = "samples/01-get-started/05_first_workflow",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "UppercaseExecutor: HELLO, WORLD!",
-                "ReverseTextExecutor: !DLROW ,OLLEH",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "01_hello_agent",
-            ProjectPath = "samples/01-get-started/01_hello_agent",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should contain a joke about a pirate.",
-                "There should be two separate joke responses — one from a non-streaming call and one from a streaming call.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "02_add_tools",
-            ProjectPath = "samples/01-get-started/02_add_tools",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            MustContain = [],
-            ExpectedOutputDescription =
-            [
-                "The output should contain information about the weather in Amsterdam.",
-                "The response should mention that it is cloudy with a high of 15°C (or equivalent), since this comes from a tool that returns a canned response.",
-                "There should be two responses — one from a non-streaming call and one from a streaming call.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "03_multi_turn",
-            ProjectPath = "samples/01-get-started/03_multi_turn",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should contain a joke about a pirate.",
-                "After the initial joke, there should be a modified version that includes emojis and is told in the voice of a pirate's parrot.",
-                "The pattern repeats: first a non-streaming pirate joke + parrot version, then a streaming pirate joke + parrot version.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "04_memory",
-            ProjectPath = "samples/01-get-started/04_memory",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            MustContain =
-            [
-                ">> Use session with blank memory",
-                ">> Use deserialized session with previously created memories",
-                ">> Read memories using memory component",
-                "MEMORY - User Name:",
-                "MEMORY - User Age:",
-                ">> Use new session with previously created memories",
-            ],
-            ExpectedOutputDescription =
-            [
-                "In the 'Use session with blank memory' section, the agent should respond to the user's messages. It may ask for the user's name or age if not yet known.",
-                "In the 'Use deserialized session with previously created memories' section, the agent should correctly recall that the user's name is Ruaidhrí and age is 20.",
-                "The 'MEMORY - User Name:' line should show 'Ruaidhrí' (or a close transliteration).",
-                "The 'MEMORY - User Age:' line should show '20'.",
-                "In the 'Use new session with previously created memories' section, the agent should know the user's name and age from the transferred memory.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "06_host_your_agent",
-            ProjectPath = "samples/01-get-started/06_host_your_agent",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            SkipReason = "Requires Azure Functions Core Tools runtime and starts a web server.",
-        },
-    ];
-}

dotnet/eng/verify-samples/LogFileWriter.cs

@@ -1,153 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Text;
-
-namespace VerifySamples;
-
-/// <summary>
-/// Incrementally writes a sequential (non-interleaved) log file, appending after each sample completes.
-/// Thread-safe: multiple parallel tasks may call write methods concurrently.
-/// </summary>
-internal sealed class LogFileWriter : IDisposable
-{
-    private readonly string _path;
-    private readonly SemaphoreSlim _writeLock = new(1, 1);
-
-    public LogFileWriter(string path)
-    {
-        this._path = path;
-    }
-
-    /// <inheritdoc />
-    public void Dispose()
-    {
-        this._writeLock.Dispose();
-    }
-
-    /// <summary>
-    /// Writes the log file header. Call once at the start of the run.
-    /// </summary>
-    public async Task WriteHeaderAsync()
-    {
-        var sb = new StringBuilder();
-        sb.AppendLine($"Sample Verification Log — {DateTime.UtcNow:yyyy-MM-dd HH:mm:ss} UTC");
-        sb.AppendLine(new string('═', 72));
-        sb.AppendLine();
-
-        await File.WriteAllTextAsync(this._path, sb.ToString());
-    }
-
-    /// <summary>
-    /// Appends a skipped-sample entry to the log file.
-    /// </summary>
-    public async Task WriteSkippedAsync(string name, string reason)
-    {
-        var sb = new StringBuilder();
-        sb.AppendLine($"── {name} ──");
-        sb.AppendLine($"Status: SKIPPED — {reason}");
-        sb.AppendLine();
-
-        await this.AppendAsync(sb.ToString());
-    }
-
-    /// <summary>
-    /// Appends a completed sample's full output section to the log file.
-    /// </summary>
-    public async Task WriteSampleResultAsync(VerificationResult result)
-    {
-        var sb = new StringBuilder();
-        sb.AppendLine(new string('─', 72));
-        sb.AppendLine($"── {result.SampleName} ──");
-        sb.AppendLine($"Status: {(result.Passed ? "PASSED" : "FAILED")}");
-        sb.AppendLine();
-
-        foreach (var line in result.LogLines)
-        {
-            sb.AppendLine(line);
-        }
-
-        sb.AppendLine();
-
-        if (!string.IsNullOrWhiteSpace(result.Stdout))
-        {
-            sb.AppendLine("--- stdout ---");
-            sb.AppendLine(result.Stdout.TrimEnd());
-            sb.AppendLine("--- end stdout ---");
-            sb.AppendLine();
-        }
-
-        if (!string.IsNullOrWhiteSpace(result.Stderr))
-        {
-            sb.AppendLine("--- stderr ---");
-            sb.AppendLine(result.Stderr.TrimEnd());
-            sb.AppendLine("--- end stderr ---");
-            sb.AppendLine();
-        }
-
-        if (result.Failures.Count > 0)
-        {
-            sb.AppendLine("Failures:");
-            foreach (var failure in result.Failures)
-            {
-                sb.AppendLine($"  ✗ {failure}");
-            }
-
-            sb.AppendLine();
-        }
-
-        if (result.AIReasoning is not null)
-        {
-            sb.AppendLine("AI Reasoning:");
-            sb.AppendLine(result.AIReasoning);
-            sb.AppendLine();
-        }
-
-        await this.AppendAsync(sb.ToString());
-    }
-
-    /// <summary>
-    /// Appends the final summary section and elapsed time to the log file.
-    /// </summary>
-    public async Task WriteSummaryAsync(
-        IReadOnlyList<VerificationResult> orderedResults,
-        IReadOnlyList<(string Name, string Reason)> skipped,
-        TimeSpan elapsed)
-    {
-        var passCount = orderedResults.Count(r => r.Passed);
-        var failCount = orderedResults.Count(r => !r.Passed);
-
-        var sb = new StringBuilder();
-        sb.AppendLine(new string('═', 72));
-        sb.AppendLine("SUMMARY");
-        sb.AppendLine();
-
-        foreach (var result in orderedResults)
-        {
-            sb.AppendLine($"  {(result.Passed ? "✓" : "✗")} {result.SampleName}: {result.Summary}");
-        }
-
-        foreach (var (name, reason) in skipped)
-        {
-            sb.AppendLine($"  ○ {name}: Skipped — {reason}");
-        }
-
-        sb.AppendLine();
-        sb.AppendLine($"Results: {passCount} passed{(failCount > 0 ? $", {failCount} failed" : "")}{(skipped.Count > 0 ? $", {skipped.Count} skipped" : "")}");
-        sb.AppendLine($"Elapsed: {elapsed.Hours:D2}:{elapsed.Minutes:D2}:{elapsed.Seconds:D2}");
-
-        await this.AppendAsync(sb.ToString());
-    }
-
-    private async Task AppendAsync(string text)
-    {
-        await this._writeLock.WaitAsync();
-        try
-        {
-            await File.AppendAllTextAsync(this._path, text);
-        }
-        finally
-        {
-            this._writeLock.Release();
-        }
-    }
-}

dotnet/eng/verify-samples/Program.cs

@@ -1,98 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-// This tool runs the 01-get-started, 02-agents, and 03-workflows samples and verifies their output.
-// Deterministic samples are verified with exact string matching.
-// Non-deterministic (LLM) samples are verified using an agent-framework agent.
-//
-// Usage:
-//   dotnet run                                          # Run all samples
-//   dotnet run -- 01_hello_agent 05_first_workflow      # Run specific samples by name
-//   dotnet run -- --category 01-get-started             # Run the 01-get-started category
-//   dotnet run -- --category 02-agents                  # Run the 02-agents category
-//   dotnet run -- --category 03-workflows               # Run the 03-workflows category
-//   dotnet run -- --parallel 16                         # Run up to 16 samples concurrently
-//   dotnet run -- --log results.log                     # Write sequential log to file
-//   dotnet run -- --csv results.csv                     # Write CSV summary to file
-//
-// Required environment variables (for AI-powered samples):
-//   AZURE_OPENAI_ENDPOINT
-//   AZURE_OPENAI_DEPLOYMENT_NAME (optional, defaults to gpt-5-mini)
-
-using System.Diagnostics;
-using Azure.AI.OpenAI;
-using Azure.Identity;
-using VerifySamples;
-
-var options = VerifyOptions.Parse(args);
-if (options is null)
-{
-    return 1;
-}
-
-var stopwatch = Stopwatch.StartNew();
-
-// Resolve the dotnet/ root directory (verify-samples is at dotnet/eng/verify-samples/)
-var dotnetRoot = Path.GetFullPath(Path.Combine(AppContext.BaseDirectory, "..", "..", "..", "..", ".."));
-if (!File.Exists(Path.Combine(dotnetRoot, "agent-framework-dotnet.slnx")))
-{
-    dotnetRoot = Path.GetFullPath(Path.Combine(Directory.GetCurrentDirectory(), "..", ".."));
-}
-
-// Set up the AI verifier
-var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
-var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5-mini";
-
-OpenAI.Chat.ChatClient? chatClient = null;
-if (!string.IsNullOrEmpty(endpoint))
-{
-    chatClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
-        .GetChatClient(deploymentName);
-}
-
-// Set up optional log file writer
-LogFileWriter? logWriter = null;
-if (options.LogFilePath is not null)
-{
-    logWriter = new LogFileWriter(options.LogFilePath);
-    await logWriter.WriteHeaderAsync();
-}
-
-try
-{
-    // Run all samples
-    var reporter = new ConsoleReporter();
-    var verifier = new SampleVerifier(chatClient);
-    var orchestrator = new VerificationOrchestrator(verifier, reporter, dotnetRoot, TimeSpan.FromMinutes(3), logWriter);
-
-    var run = await orchestrator.RunAllAsync(options.Samples, options.MaxParallelism);
-
-    stopwatch.Stop();
-
-    // Print summary
-    var orderedResults = run.SampleOrder
-        .Where(run.Results.ContainsKey)
-        .Select(name => run.Results[name])
-        .ToList();
-
-    reporter.PrintSummary(orderedResults, run.Skipped, stopwatch.Elapsed);
-
-    // Write log file summary
-    if (logWriter is not null)
-    {
-        await logWriter.WriteSummaryAsync(orderedResults, run.Skipped, stopwatch.Elapsed);
-        Console.WriteLine($"Log written to: {options.LogFilePath}");
-    }
-
-    // Write CSV summary
-    if (options.CsvFilePath is not null)
-    {
-        await CsvResultWriter.WriteAsync(options.CsvFilePath, orderedResults, run.Skipped, options.Samples);
-        Console.WriteLine($"CSV written to: {options.CsvFilePath}");
-    }
-
-    return orderedResults.Any(r => !r.Passed) ? 1 : 0;
-}
-finally
-{
-    logWriter?.Dispose();
-}

dotnet/eng/verify-samples/SampleDefinition.cs

@@ -1,79 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// Describes a sample to verify, including its expected output.
-/// </summary>
-internal sealed class SampleDefinition
-{
-    /// <summary>
-    /// Display name for the sample (e.g., "01_hello_agent").
-    /// </summary>
-    public required string Name { get; init; }
-
-    /// <summary>
-    /// Relative path from the dotnet/ directory to the sample project directory.
-    /// </summary>
-    public required string ProjectPath { get; init; }
-
-    /// <summary>
-    /// Environment variables that the sample requires for a meaningful run.
-    /// The runner checks these before running and will skip the sample if any are unset,
-    /// recording a skip reason that indicates which required variables are missing.
-    /// </summary>
-    public string[] RequiredEnvironmentVariables { get; init; } = [];
-
-    /// <summary>
-    /// Environment variables that the sample can use but typically has fallbacks or defaults for.
-    /// If these are not set, the sample might prompt or behave interactively, which could cause
-    /// automated verification to hang. The runner checks these and skips the sample if they are unset
-    /// to avoid non-deterministic or blocking behavior in automated runs.
-    /// </summary>
-    public string[] OptionalEnvironmentVariables { get; init; } = [];
-
-    /// <summary>
-    /// If set, the sample is skipped with this reason.
-    /// Use only for structural reasons (e.g., web server, multi-process, needs external service).
-    /// Do NOT use for missing environment variables — those are checked dynamically.
-    /// </summary>
-    public string? SkipReason { get; init; }
-
-    /// <summary>
-    /// Substrings that must appear in stdout for the sample to pass.
-    /// Used for deterministic verification.
-    /// </summary>
-    public string[] MustContain { get; init; } = [];
-
-    /// <summary>
-    /// Substrings that must not appear in stdout for the sample to pass.
-    /// </summary>
-    public string[] MustNotContain { get; init; } = [];
-
-    /// <summary>
-    /// If true, <see cref="MustContain"/> entries cover the entire expected output —
-    /// no AI verification is needed.
-    /// </summary>
-    public bool IsDeterministic { get; init; }
-
-    /// <summary>
-    /// Natural-language description of what the sample output should look like.
-    /// Used by the AI verifier for non-deterministic samples.
-    /// Each entry describes one aspect of the expected output that should be verified.
-    /// </summary>
-    public string[] ExpectedOutputDescription { get; init; } = [];
-
-    /// <summary>
-    /// Sequence of stdin inputs to feed to the sample process.
-    /// Each entry is written as a line (followed by newline) to the process stdin.
-    /// A <c>null</c> entry inserts a delay without writing anything.
-    /// Inputs are sent with a short delay between each to allow the process to prompt.
-    /// </summary>
-    public string?[] Inputs { get; init; } = [];
-
-    /// <summary>
-    /// Delay in milliseconds between each input line. Default is 2000ms.
-    /// Increase for samples that need more time between prompts (e.g., LLM calls between inputs).
-    /// </summary>
-    public int InputDelayMs { get; init; } = 2000;
-}

dotnet/eng/verify-samples/SampleRunner.cs

@@ -1,132 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Diagnostics;
-
-namespace VerifySamples;
-
-/// <summary>
-/// Result of running a sample process.
-/// </summary>
-internal sealed record SampleRunResult(
-    string Stdout,
-    string Stderr,
-    int ExitCode,
-    TimeSpan Elapsed);
-
-/// <summary>
-/// Runs a sample project via <c>dotnet run</c> and captures its output.
-/// </summary>
-internal static class SampleRunner
-{
-    /// <summary>
-    /// Runs <c>dotnet run --framework net10.0</c> in the given project directory.
-    /// </summary>
-    public static Task<SampleRunResult> RunAsync(
-        string projectPath,
-        TimeSpan timeout,
-        CancellationToken cancellationToken = default)
-        => RunAsync(projectPath, "run --framework net10.0", timeout, inputs: null, inputDelayMs: 0, cancellationToken: cancellationToken);
-
-    /// <summary>
-    /// Runs <c>dotnet run --framework net10.0</c> with stdin inputs.
-    /// </summary>
-    public static Task<SampleRunResult> RunAsync(
-        string projectPath,
-        TimeSpan timeout,
-        string?[]? inputs,
-        int inputDelayMs = 2000,
-        CancellationToken cancellationToken = default)
-        => RunAsync(projectPath, "run --framework net10.0", timeout, inputs, inputDelayMs, cancellationToken);
-
-    /// <summary>
-    /// Runs an arbitrary <c>dotnet</c> command in the given working directory.
-    /// </summary>
-    public static async Task<SampleRunResult> RunAsync(
-        string workingDirectory,
-        string dotnetArgs,
-        TimeSpan timeout,
-        string?[]? inputs = null,
-        int inputDelayMs = 0,
-        CancellationToken cancellationToken = default)
-    {
-        var psi = new ProcessStartInfo
-        {
-            FileName = "dotnet",
-            Arguments = dotnetArgs,
-            WorkingDirectory = workingDirectory,
-            RedirectStandardOutput = true,
-            RedirectStandardError = true,
-            RedirectStandardInput = inputs is { Length: > 0 },
-            UseShellExecute = false,
-            CreateNoWindow = true,
-        };
-
-        var sw = Stopwatch.StartNew();
-
-        using var process = new Process { StartInfo = psi };
-        process.Start();
-
-        var stdoutTask = process.StandardOutput.ReadToEndAsync(cancellationToken);
-        var stderrTask = process.StandardError.ReadToEndAsync(cancellationToken);
-
-        // Feed stdin inputs with delays if configured
-        if (inputs is { Length: > 0 })
-        {
-            _ = Task.Run(async () =>
-            {
-                try
-                {
-                    foreach (var input in inputs)
-                    {
-                        await Task.Delay(inputDelayMs, cancellationToken);
-                        if (input is not null)
-                        {
-                            await process.StandardInput.WriteLineAsync(input.AsMemory(), cancellationToken);
-                            await process.StandardInput.FlushAsync(cancellationToken);
-                        }
-                    }
-
-                    process.StandardInput.Close();
-                }
-                catch (Exception ex) when (ex is IOException or ObjectDisposedException or OperationCanceledException)
-                {
-                    // Process may have exited before all inputs were sent
-                }
-            }, cancellationToken);
-        }
-
-        using var cts = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
-        cts.CancelAfter(timeout);
-
-        try
-        {
-            await process.WaitForExitAsync(cts.Token);
-        }
-        catch (OperationCanceledException) when (!cancellationToken.IsCancellationRequested)
-        {
-            // Timeout — kill the process
-            try
-            {
-                process.Kill(entireProcessTree: true);
-            }
-            catch
-            {
-                // Best effort
-            }
-
-            sw.Stop();
-            return new SampleRunResult(
-                Stdout: await stdoutTask,
-                Stderr: $"TIMEOUT: Sample did not complete within {timeout.TotalSeconds}s.\n{await stderrTask}",
-                ExitCode: -1,
-                Elapsed: sw.Elapsed);
-        }
-
-        sw.Stop();
-        return new SampleRunResult(
-            Stdout: await stdoutTask,
-            Stderr: await stderrTask,
-            ExitCode: process.ExitCode,
-            Elapsed: sw.Elapsed);
-    }
-}

dotnet/eng/verify-samples/SampleVerifier.cs

@@ -1,202 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Text.Json.Serialization;
-using Microsoft.Agents.AI;
-using Microsoft.Extensions.AI;
-using OpenAI.Chat;
-
-namespace VerifySamples;
-
-/// <summary>
-/// Verifies sample output using deterministic checks and an AI agent
-/// for non-deterministic output validation.
-/// </summary>
-internal sealed class SampleVerifier
-{
-    private readonly AIAgent? _verifierAgent;
-
-    /// <summary>
-    /// Creates a verifier. If <paramref name="chatClient"/> is provided,
-    /// AI-based verification is available for non-deterministic samples.
-    /// </summary>
-    public SampleVerifier(ChatClient? chatClient = null)
-    {
-        if (chatClient is not null)
-        {
-            this._verifierAgent = chatClient.AsAIAgent(
-                instructions: """
-                    You are a test output verifier. You will be given:
-                    1. The actual stdout output of a program
-                    2. A list of expectations about what the output should contain or demonstrate
-
-                    Your job is to determine whether the actual output satisfies each expectation.
-                    Be reasonable — the output comes from an LLM so exact wording won't match, but the
-                    semantic intent should be clearly satisfied.
-                    """,
-                name: "OutputVerifier");
-        }
-    }
-
-    /// <summary>
-    /// Verifies the output of a sample run against its definition.
-    /// </summary>
-    public async Task<VerificationResult> VerifyAsync(SampleDefinition sample, SampleRunResult run)
-    {
-        var failures = new List<string>();
-
-        // 1. Exit code check
-        if (run.ExitCode != 0)
-        {
-            failures.Add($"Exit code was {run.ExitCode}, expected 0. Stderr: {Truncate(run.Stderr, 500)}");
-        }
-
-        // 2. Must-contain checks
-        foreach (var expected in sample.MustContain)
-        {
-            if (!run.Stdout.Contains(expected, StringComparison.Ordinal))
-            {
-                failures.Add($"Output missing expected substring: \"{expected}\"");
-            }
-        }
-
-        // 3. Must-not-contain checks
-        foreach (var unexpected in sample.MustNotContain)
-        {
-            if (run.Stdout.Contains(unexpected, StringComparison.Ordinal))
-            {
-                failures.Add($"Output contains unexpected substring: \"{unexpected}\"");
-            }
-        }
-
-        // 4. AI verification for non-deterministic samples
-        string? aiReasoning = null;
-        if (!sample.IsDeterministic && sample.ExpectedOutputDescription.Length > 0)
-        {
-            if (this._verifierAgent is null)
-            {
-                failures.Add("AI verification required but no AI agent configured (missing AZURE_OPENAI_ENDPOINT).");
-            }
-            else
-            {
-                var aiResult = await this.VerifyWithAIAsync(run.Stdout, sample.ExpectedOutputDescription);
-                aiReasoning = aiResult.Reasoning;
-
-                foreach (var unmet in aiResult.UnmetExpectations)
-                {
-                    failures.Add($"AI expectation not met: {unmet}");
-                }
-            }
-        }
-
-        bool passed = failures.Count == 0;
-        return new VerificationResult
-        {
-            SampleName = sample.Name,
-            Passed = passed,
-            Summary = passed ? "All checks passed" : $"{failures.Count} check(s) failed",
-            Failures = failures,
-            AIReasoning = aiReasoning,
-        };
-    }
-
-    private async Task<(string Reasoning, List<string> UnmetExpectations)> VerifyWithAIAsync(
-        string actualOutput,
-        string[] expectations)
-    {
-        var expectationList = string.Join("\n", expectations.Select((e, i) => $"  {i + 1}. {e}"));
-        var prompt = $"""
-            Actual program output:
-            ---
-            {Truncate(actualOutput, 4000)}
-            ---
-
-            Expectations to verify:
-            {expectationList}
-
-            Does the output satisfy all expectations?
-            """;
-
-        try
-        {
-            var response = await this._verifierAgent!.RunAsync<AIVerificationResponse>(prompt);
-            var result = response.Result;
-
-            if (result is null)
-            {
-                return ($"AI verification returned null result. Raw: {response.Text}", ["AI verification returned null result."]);
-            }
-
-            var reasoning = result.Reasoning ?? "(no reasoning provided)";
-
-            // Collect unmet expectations as individual failures
-            var unmet = new List<string>();
-            if (result.ExpectationResults is { Count: > 0 })
-            {
-                foreach (var er in result.ExpectationResults.Where(er => !er.Met))
-                {
-                    var detail = string.IsNullOrWhiteSpace(er.Detail) ? er.Expectation : $"{er.Expectation} — {er.Detail}";
-                    unmet.Add(detail ?? "Unknown expectation");
-                }
-
-                // If the model flagged overall failure but all individual expectations were met,
-                // still treat as failure using the overall reasoning.
-                if (unmet.Count == 0 && !result.Pass)
-                {
-                    unmet.Add(reasoning);
-                }
-            }
-            else if (!result.Pass)
-            {
-                // Fallback: no per-expectation detail but overall pass is false
-                unmet.Add(reasoning);
-            }
-
-            return (reasoning, unmet);
-        }
-        catch (Exception ex)
-        {
-            return ($"AI verification error: {ex.Message}", [$"AI verification error: {ex.Message}"]);
-        }
-    }
-
-    private static string Truncate(string text, int maxLength)
-        => text.Length <= maxLength ? text : text[..maxLength] + "... (truncated)";
-}
-
-/// <summary>
-/// Structured response from the AI verification agent.
-/// </summary>
-[System.Diagnostics.CodeAnalysis.SuppressMessage("Performance", "CA1812:Avoid uninstantiated internal classes", Justification = "Instantiated by JSON deserialization via RunAsync<T>.")]
-internal sealed class AIVerificationResponse
-{
-    /// <summary>Whether all expectations were met.</summary>
-    [JsonPropertyName("pass")]
-    public bool Pass { get; set; }
-
-    /// <summary>Brief explanation of the overall assessment.</summary>
-    [JsonPropertyName("reasoning")]
-    public string? Reasoning { get; set; }
-
-    /// <summary>Per-expectation results.</summary>
-    [JsonPropertyName("expectation_results")]
-    public List<ExpectationResult>? ExpectationResults { get; set; }
-}
-
-/// <summary>
-/// Result for an individual expectation check.
-/// </summary>
-[System.Diagnostics.CodeAnalysis.SuppressMessage("Performance", "CA1812:Avoid uninstantiated internal classes", Justification = "Instantiated by JSON deserialization via RunAsync<T>.")]
-internal sealed class ExpectationResult
-{
-    /// <summary>The expectation text that was evaluated.</summary>
-    [JsonPropertyName("expectation")]
-    public string? Expectation { get; set; }
-
-    /// <summary>Whether this expectation was met.</summary>
-    [JsonPropertyName("met")]
-    public bool Met { get; set; }
-
-    /// <summary>Detail about how the expectation was or was not met.</summary>
-    [JsonPropertyName("detail")]
-    public string? Detail { get; set; }
-}

dotnet/eng/verify-samples/VerificationOrchestrator.cs

@@ -1,197 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Collections.Concurrent;
-
-namespace VerifySamples;
-
-/// <summary>
-/// Orchestrates sample verification: filters, runs in parallel, and collects results.
-/// </summary>
-internal sealed class VerificationOrchestrator
-{
-    private readonly SampleVerifier _verifier;
-    private readonly ConsoleReporter _reporter;
-    private readonly LogFileWriter? _logWriter;
-    private readonly string _dotnetRoot;
-    private readonly TimeSpan _timeout;
-
-    public VerificationOrchestrator(
-        SampleVerifier verifier,
-        ConsoleReporter reporter,
-        string dotnetRoot,
-        TimeSpan timeout,
-        LogFileWriter? logWriter = null)
-    {
-        this._verifier = verifier;
-        this._reporter = reporter;
-        this._logWriter = logWriter;
-        this._dotnetRoot = dotnetRoot;
-        this._timeout = timeout;
-    }
-
-    /// <summary>
-    /// The result of running all samples through the orchestrator.
-    /// </summary>
-    internal sealed record RunAllResult(
-        ConcurrentDictionary<string, VerificationResult> Results,
-        List<(string Name, string Reason)> Skipped,
-        List<string> SampleOrder);
-
-    /// <summary>
-    /// Filters samples, runs the runnable ones in parallel, and returns all results.
-    /// </summary>
-    public async Task<RunAllResult> RunAllAsync(
-        IReadOnlyList<SampleDefinition> samples,
-        int maxParallelism)
-    {
-        var skipped = new List<(string Name, string Reason)>();
-        var runnableSamples = new List<SampleDefinition>();
-        var sampleOrder = new List<string>();
-
-        // Separate samples into skipped and runnable
-        foreach (var sample in samples)
-        {
-            sampleOrder.Add(sample.Name);
-
-            if (sample.SkipReason is not null)
-            {
-                skipped.Add((sample.Name, sample.SkipReason));
-                this._reporter.WriteLineWithPrefix(sample.Name, $"SKIPPED — {sample.SkipReason}", ConsoleColor.Yellow);
-
-                if (this._logWriter is not null)
-                {
-                    await this._logWriter.WriteSkippedAsync(sample.Name, sample.SkipReason);
-                }
-
-                continue;
-            }
-
-            var missingRequired = sample.RequiredEnvironmentVariables
-                .Where(v => string.IsNullOrEmpty(Environment.GetEnvironmentVariable(v)))
-                .ToList();
-
-            var missingOptional = sample.OptionalEnvironmentVariables
-                .Where(v => string.IsNullOrEmpty(Environment.GetEnvironmentVariable(v)))
-                .ToList();
-
-            if (missingRequired.Count > 0 || missingOptional.Count > 0)
-            {
-                var reasons = new List<string>();
-                if (missingRequired.Count > 0)
-                {
-                    reasons.Add($"Missing required: {string.Join(", ", missingRequired)}");
-                }
-
-                if (missingOptional.Count > 0)
-                {
-                    reasons.Add($"Missing optional (would cause console prompt hang): {string.Join(", ", missingOptional)}");
-                }
-
-                var skipReason = string.Join("; ", reasons);
-                skipped.Add((sample.Name, skipReason));
-                this._reporter.WriteLineWithPrefix(sample.Name, $"SKIPPED — {skipReason}", ConsoleColor.Yellow);
-
-                if (this._logWriter is not null)
-                {
-                    await this._logWriter.WriteSkippedAsync(sample.Name, skipReason);
-                }
-
-                continue;
-            }
-
-            runnableSamples.Add(sample);
-        }
-
-        // Run samples in parallel
-        var results = new ConcurrentDictionary<string, VerificationResult>();
-        var semaphore = new SemaphoreSlim(maxParallelism);
-
-        this._reporter.WriteLineWithPrefix(
-            "runner", $"Running {runnableSamples.Count} samples (max {maxParallelism} parallel)...");
-
-        try
-        {
-            var tasks = runnableSamples.Select(sample => this.RunSingleAsync(sample, results, semaphore)).ToArray();
-            await Task.WhenAll(tasks);
-        }
-        finally
-        {
-            semaphore.Dispose();
-        }
-
-        return new RunAllResult(results, skipped, sampleOrder);
-    }
-
-    private async Task RunSingleAsync(
-        SampleDefinition sample,
-        ConcurrentDictionary<string, VerificationResult> results,
-        SemaphoreSlim semaphore)
-    {
-        await semaphore.WaitAsync();
-        try
-        {
-            var log = new List<string>();
-            log.Add($"[{sample.Name}] Running...");
-            this._reporter.WriteLineWithPrefix(sample.Name, "Running...");
-
-            var projectPath = Path.Combine(this._dotnetRoot, sample.ProjectPath);
-            var run = sample.Inputs.Length > 0
-                ? await SampleRunner.RunAsync(projectPath, this._timeout, sample.Inputs, sample.InputDelayMs)
-                : await SampleRunner.RunAsync(projectPath, this._timeout);
-
-            log.Add($"[{sample.Name}] Completed ({run.Elapsed.TotalSeconds:F1}s, exit={run.ExitCode})");
-            this._reporter.WriteLineWithPrefix(
-                sample.Name, $"Completed ({run.Elapsed.TotalSeconds:F1}s, exit={run.ExitCode}). Verifying...");
-
-            var result = await this._verifier.VerifyAsync(sample, run);
-
-            if (result.Passed)
-            {
-                log.Add($"[{sample.Name}] PASSED");
-                this._reporter.WriteLineWithPrefix(sample.Name, "PASSED", ConsoleColor.Green);
-            }
-            else
-            {
-                log.Add($"[{sample.Name}] FAILED");
-                this._reporter.WriteLineWithPrefix(sample.Name, "FAILED", ConsoleColor.Red);
-                foreach (var failure in result.Failures)
-                {
-                    log.Add($"[{sample.Name}]   ✗ {failure}");
-                    this._reporter.WriteLineWithPrefix(sample.Name, $"  ✗ {failure}", ConsoleColor.Red);
-                }
-            }
-
-            if (result.AIReasoning is not null)
-            {
-                log.Add($"[{sample.Name}]   AI: {result.AIReasoning}");
-                this._reporter.WriteLineWithPrefix(
-                    sample.Name, $"  AI: {Truncate(result.AIReasoning, 300)}", ConsoleColor.DarkGray);
-            }
-
-            var verificationResult = new VerificationResult
-            {
-                SampleName = result.SampleName,
-                Passed = result.Passed,
-                Summary = result.Summary,
-                Failures = result.Failures,
-                AIReasoning = result.AIReasoning,
-                Stdout = run.Stdout,
-                Stderr = run.Stderr,
-                LogLines = log,
-            };
-            results[sample.Name] = verificationResult;
-
-            if (this._logWriter is not null)
-            {
-                await this._logWriter.WriteSampleResultAsync(verificationResult);
-            }
-        }
-        finally
-        {
-            semaphore.Release();
-        }
-    }
-
-    private static string Truncate(string text, int maxLength)
-        => text.Length <= maxLength ? text : text[..maxLength] + "...";
-}

dotnet/eng/verify-samples/VerificationResult.cs

@@ -1,31 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// The result of verifying a single sample.
-/// </summary>
-internal sealed class VerificationResult
-{
-    public required string SampleName { get; init; }
-    public required bool Passed { get; init; }
-    public required string Summary { get; init; }
-    public List<string> Failures { get; init; } = [];
-    public string? AIReasoning { get; init; }
-
-    /// <summary>
-    /// The sample's stdout output, captured for log file output.
-    /// </summary>
-    public string? Stdout { get; init; }
-
-    /// <summary>
-    /// The sample's stderr output, captured for log file output.
-    /// </summary>
-    public string? Stderr { get; init; }
-
-    /// <summary>
-    /// Per-sample log lines, buffered during parallel execution
-    /// and written sequentially to the log file.
-    /// </summary>
-    public List<string> LogLines { get; init; } = [];
-}

dotnet/eng/verify-samples/VerifyOptions.cs

@@ -1,124 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// Parsed command-line options for the sample verification tool.
-/// </summary>
-internal sealed class VerifyOptions
-{
-    /// <summary>
-    /// Maximum number of samples to run concurrently.
-    /// </summary>
-    public int MaxParallelism { get; init; } = 8;
-
-    /// <summary>
-    /// Path to write a CSV summary file, or <c>null</c> to skip.
-    /// </summary>
-    public string? CsvFilePath { get; init; }
-
-    /// <summary>
-    /// Path to write a sequential log file, or <c>null</c> to skip.
-    /// </summary>
-    public string? LogFilePath { get; init; }
-
-    /// <summary>
-    /// The filtered list of samples to process.
-    /// </summary>
-    public required IReadOnlyList<SampleDefinition> Samples { get; init; }
-
-    /// <summary>
-    /// All known sample set registries, keyed by category name.
-    /// </summary>
-    private static readonly Dictionary<string, IReadOnlyList<SampleDefinition>> s_sampleSets =
-        new(StringComparer.OrdinalIgnoreCase)
-        {
-            ["01-get-started"] = GetStartedSamples.All,
-            ["02-agents"] = AgentsSamples.All,
-            ["03-workflows"] = WorkflowSamples.All,
-        };
-
-    /// <summary>
-    /// Parses command-line arguments and resolves the sample list.
-    /// Returns <c>null</c> and writes to stderr if the arguments are invalid.
-    /// </summary>
-    public static VerifyOptions? Parse(string[] args)
-    {
-        var argList = args.ToList();
-
-        var categoryFilter = ExtractArg(argList, "--category");
-        var logFilePath = ExtractArg(argList, "--log");
-        var csvFilePath = ExtractArg(argList, "--csv");
-
-        int maxParallelism = 8;
-        var parallelArg = ExtractArg(argList, "--parallel");
-        if (parallelArg is not null && int.TryParse(parallelArg, out var p) && p > 0)
-        {
-            maxParallelism = p;
-        }
-
-        HashSet<string>? nameFilter = null;
-        if (argList.Count > 0)
-        {
-            nameFilter = argList.ToHashSet(StringComparer.OrdinalIgnoreCase);
-        }
-
-        // Build the sample list
-        IReadOnlyList<SampleDefinition> samples;
-        if (categoryFilter is not null)
-        {
-            if (!s_sampleSets.TryGetValue(categoryFilter, out var categoryList))
-            {
-                Console.Error.WriteLine(
-                    $"Unknown category '{categoryFilter}'. Available: {string.Join(", ", s_sampleSets.Keys)}");
-                return null;
-            }
-
-            samples = categoryList;
-        }
-        else
-        {
-            samples = s_sampleSets.Values.SelectMany(s => s).ToList();
-        }
-
-        if (nameFilter is not null)
-        {
-            samples = samples.Where(s => nameFilter.Contains(s.Name)).ToList();
-        }
-
-        if (samples.Count == 0)
-        {
-            var allNames = s_sampleSets.Values.SelectMany(s => s).Select(s => s.Name);
-            Console.Error.WriteLine($"No matching samples found. Available: {string.Join(", ", allNames)}");
-            return null;
-        }
-
-        return new VerifyOptions
-        {
-            MaxParallelism = maxParallelism,
-            LogFilePath = logFilePath,
-            CsvFilePath = csvFilePath,
-            Samples = samples,
-        };
-    }
-
-    private static string? ExtractArg(List<string> list, string flag)
-    {
-        var idx = list.IndexOf(flag);
-        if (idx < 0)
-        {
-            return null;
-        }
-
-        if (idx + 1 >= list.Count)
-        {
-            Console.Error.WriteLine($"Missing value for {flag}.");
-            list.RemoveAt(idx);
-            return null;
-        }
-
-        var value = list[idx + 1];
-        list.RemoveRange(idx, 2);
-        return value;
-    }
-}

dotnet/eng/verify-samples/WorkflowSamples.cs

@@ -1,525 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace VerifySamples;
-
-/// <summary>
-/// Defines the expected behavior for each sample in 03-workflows.
-/// </summary>
-internal static class WorkflowSamples
-{
-    public static IReadOnlyList<SampleDefinition> All { get; } =
-    [
-        // ───────────────────────────────────────────────────────────────────
-        // _StartHere
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_01_Streaming",
-            ProjectPath = "samples/03-workflows/_StartHere/01_Streaming",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "UppercaseExecutor: HELLO, WORLD!",
-                "ReverseTextExecutor: !DLROW ,OLLEH",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_02_AgentsInWorkflows",
-            ProjectPath = "samples/03-workflows/_StartHere/02_AgentsInWorkflows",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show agent responses from a translation workflow.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_03_AgentWorkflowPatterns",
-            ProjectPath = "samples/03-workflows/_StartHere/03_AgentWorkflowPatterns",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            Inputs = ["sequential"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription =
-            [
-                "The output should show a sequential workflow pattern with multiple agents executing tasks in order.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_04_MultiModelService",
-            ProjectPath = "samples/03-workflows/_StartHere/04_MultiModelService",
-            RequiredEnvironmentVariables = ["BEDROCK_ACCESS_KEY", "BEDROCK_SECRET_KEY", "ANTHROPIC_API_KEY", "OPENAI_API_KEY"],
-            SkipReason = "Requires multiple external provider API keys (Bedrock, Anthropic, OpenAI).",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_05_SubWorkflows",
-            ProjectPath = "samples/03-workflows/_StartHere/05_SubWorkflows",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "=== Sub-Workflow Demonstration ===",
-                "Final Output:",
-                "=== Main Workflow Completed ===",
-                "Sample Complete: Workflows can be composed hierarchically using sub-workflows",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_06_MixedWorkflowAgentsAndExecutors",
-            ProjectPath = "samples/03-workflows/_StartHere/06_MixedWorkflowAgentsAndExecutors",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            Inputs = ["What is 2 plus 2?"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription =
-            [
-                "The output should show agents and executors working together to process a user question.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_StartHere_07_WriterCriticWorkflow",
-            ProjectPath = "samples/03-workflows/_StartHere/07_WriterCriticWorkflow",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            MustContain = ["=== Writer-Critic Iteration Workflow ==="],
-            ExpectedOutputDescription =
-            [
-                "The output should show a writer-critic iteration workflow with writer and critic sections.",
-                "The critic should either approve or request revisions.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Agents
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Agents_CustomAgentExecutors",
-            ProjectPath = "samples/03-workflows/Agents/CustomAgentExecutors",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show custom workflow events including slogan generation and feedback.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Agents_FoundryAgent",
-            ProjectPath = "samples/03-workflows/Agents/FoundryAgent",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            SkipReason = "Requires Azure AI Foundry project endpoint.",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Agents_GroupChatToolApproval",
-            ProjectPath = "samples/03-workflows/Agents/GroupChatToolApproval",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            MustContain = ["Starting group chat workflow for software deployment..."],
-            ExpectedOutputDescription =
-            [
-                "The output should show a group chat workflow with QA and DevOps agents for software deployment.",
-                "There should be approval requests for tool calls.",
-                "The workflow should show interaction between QA and DevOps agents toward deployment.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Agents_WorkflowAsAnAgent",
-            ProjectPath = "samples/03-workflows/Agents/WorkflowAsAnAgent",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            Inputs = ["hello", "exit"],
-            InputDelayMs = 5000,
-            ExpectedOutputDescription =
-            [
-                "The output should show a conversational workflow responding to the user's hello message.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Checkpoint
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Checkpoint_CheckpointAndRehydrate",
-            ProjectPath = "samples/03-workflows/Checkpoint/CheckpointAndRehydrate",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "Workflow completed with result:",
-                "Number of checkpoints created:",
-                "Hydrating a new workflow instance from the 6th checkpoint.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Checkpoint_CheckpointAndResume",
-            ProjectPath = "samples/03-workflows/Checkpoint/CheckpointAndResume",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "Workflow completed with result:",
-                "Number of checkpoints created:",
-                "Restoring from the 6th checkpoint.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Checkpoint_CheckpointWithHumanInTheLoop",
-            ProjectPath = "samples/03-workflows/Checkpoint/CheckpointWithHumanInTheLoop",
-            RequiredEnvironmentVariables = [],
-            Inputs = ["50", "25", "40", "45", "42", "50", "25", "40", "45", "42"],
-            InputDelayMs = 1000,
-            MustContain = ["found in"],
-            ExpectedOutputDescription =
-            [
-                "The output should show a number guessing game with higher/lower hints that eventually reaches the correct number.",
-                "The output should demonstrate checkpoint save and restore behavior.",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Concurrent
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Concurrent_Concurrent",
-            ProjectPath = "samples/03-workflows/Concurrent/Concurrent",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show results from concurrent agent processing.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Concurrent_MapReduce",
-            ProjectPath = "samples/03-workflows/Concurrent/MapReduce",
-            RequiredEnvironmentVariables = [],
-            MustContain =
-            [
-                "=== RUNNING WORKFLOW ===",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // ConditionalEdges
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_ConditionalEdges_01_EdgeCondition",
-            ProjectPath = "samples/03-workflows/ConditionalEdges/01_EdgeCondition",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show an email being classified as spam or not spam and processed accordingly.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_ConditionalEdges_02_SwitchCase",
-            ProjectPath = "samples/03-workflows/ConditionalEdges/02_SwitchCase",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show an ambiguous email being classified as spam, not spam, or uncertain.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_ConditionalEdges_03_MultiSelection",
-            ProjectPath = "samples/03-workflows/ConditionalEdges/03_MultiSelection",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            ExpectedOutputDescription =
-            [
-                "The output should show an email being classified and potentially routed to multiple handlers.",
-                "The output should not contain error messages or stack traces.",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // HumanInTheLoop
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_HumanInTheLoop_Basic",
-            ProjectPath = "samples/03-workflows/HumanInTheLoop/HumanInTheLoopBasic",
-            RequiredEnvironmentVariables = [],
-            Inputs = ["50", "25", "40", "45", "42"],
-            InputDelayMs = 1000,
-            MustContain = ["found in"],
-            ExpectedOutputDescription =
-            [
-                "The output should show a number guessing game with higher/lower hints that eventually reaches the correct number 42.",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Loop
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Loop",
-            ProjectPath = "samples/03-workflows/Loop",
-            RequiredEnvironmentVariables = [],
-            MustContain = ["Result:"],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // SharedStates
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_SharedStates",
-            ProjectPath = "samples/03-workflows/SharedStates",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "Total Paragraphs:",
-                "Total Words:",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Visualization
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Visualization",
-            ProjectPath = "samples/03-workflows/Visualization",
-            RequiredEnvironmentVariables = [],
-            IsDeterministic = true,
-            MustContain =
-            [
-                "Generating workflow visualization...",
-                "Mermaid string:",
-                "DiGraph string:",
-            ],
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Observability
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Observability_ApplicationInsights",
-            ProjectPath = "samples/03-workflows/Observability/ApplicationInsights",
-            RequiredEnvironmentVariables = ["APPLICATIONINSIGHTS_CONNECTION_STRING"],
-            SkipReason = "Requires Application Insights connection string.",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Observability_AspireDashboard",
-            ProjectPath = "samples/03-workflows/Observability/AspireDashboard",
-            RequiredEnvironmentVariables = [],
-            SkipReason = "Requires Aspire Dashboard / OTLP endpoint.",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Observability_WorkflowAsAnAgent",
-            ProjectPath = "samples/03-workflows/Observability/WorkflowAsAnAgent",
-            RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
-            SkipReason = "Interactive console with ReadLine loop; requires OTLP endpoint.",
-        },
-
-        // ───────────────────────────────────────────────────────────────────
-        // Declarative
-        // ───────────────────────────────────────────────────────────────────
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_ConfirmInput",
-            ProjectPath = "samples/03-workflows/Declarative/ConfirmInput",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            Inputs = ["hello", "hello"],
-            InputDelayMs = 8000,
-            ExpectedOutputDescription = ["The output should show a confirmation prompt and a user response."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_CustomerSupport",
-            ProjectPath = "samples/03-workflows/Declarative/CustomerSupport",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["My laptop won't start"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription = ["The output should show a customer support workflow processing a laptop issue, with agent responses providing troubleshooting or support."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_DeepResearch",
-            ProjectPath = "samples/03-workflows/Declarative/DeepResearch",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            SkipReason = "Requires external weather API (wttr.in).",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_ExecuteCode",
-            ProjectPath = "samples/03-workflows/Declarative/ExecuteCode",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            Inputs = ["What is 12 * 34?"],
-            InputDelayMs = 5000,
-            ExpectedOutputDescription = ["The output should show a declarative workflow executing generated code, processing a math question and producing a result."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_ExecuteWorkflow",
-            ProjectPath = "samples/03-workflows/Declarative/ExecuteWorkflow",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            SkipReason = "Requires a workflow file path as a CLI argument.",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_FunctionTools",
-            ProjectPath = "samples/03-workflows/Declarative/FunctionTools",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["What are today's specials?", "EXIT"],
-            InputDelayMs = 8000,
-            ExpectedOutputDescription = ["The output should show a workflow calling function tools (e.g. a menu plugin) to answer a question about restaurant specials."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_GenerateCode",
-            ProjectPath = "samples/03-workflows/Declarative/GenerateCode",
-            IsDeterministic = true,
-            MustContain = ["WORKFLOW: Parsing", "WORKFLOW: Defined"],
-            ExpectedOutputDescription = ["The output should show a YAML workflow being parsed and C# code being generated from it."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_HostedWorkflow",
-            ProjectPath = "samples/03-workflows/Declarative/HostedWorkflow",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            SkipReason = "Hosts a persistent workflow server that does not exit.",
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_InputArguments",
-            ProjectPath = "samples/03-workflows/Declarative/InputArguments",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["I'd like to visit Seattle", "EXIT"],
-            InputDelayMs = 8000,
-            ExpectedOutputDescription = ["The output should show a workflow capturing location input and providing travel-related information about Seattle."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_InvokeFunctionTool",
-            ProjectPath = "samples/03-workflows/Declarative/InvokeFunctionTool",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["What's the soup of the day?", "EXIT"],
-            InputDelayMs = 8000,
-            ExpectedOutputDescription = ["The output should show a workflow invoking a function tool (e.g. a menu plugin) to answer a question about the soup of the day."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_InvokeMcpTool",
-            ProjectPath = "samples/03-workflows/Declarative/InvokeMcpTool",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["Search for .NET tutorials on Microsoft Learn"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription = ["The output should show a workflow using MCP tools to search Microsoft Learn documentation and provide a summary of results."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_Marketing",
-            ProjectPath = "samples/03-workflows/Declarative/Marketing",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["A smart water bottle that tracks hydration"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription = ["The output should show a marketing workflow generating content about a smart water bottle product."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_StudentTeacher",
-            ProjectPath = "samples/03-workflows/Declarative/StudentTeacher",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["What is 18 + 27?"],
-            InputDelayMs = 3000,
-            ExpectedOutputDescription = ["The output should show a student-teacher workflow where a student asks a math question and a teacher provides the answer."],
-        },
-
-        new SampleDefinition
-        {
-            Name = "Workflow_Declarative_ToolApproval",
-            ProjectPath = "samples/03-workflows/Declarative/ToolApproval",
-            RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
-            OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-            Inputs = ["Search for .NET tutorials", "EXIT"],
-            InputDelayMs = 8000,
-            ExpectedOutputDescription = ["The output should show a workflow using an MCP tool with approval to search Microsoft Learn, followed by an exit from the input loop."],
-        },
-    ];
-}

dotnet/eng/verify-samples/verify-samples.csproj

@@ -1,24 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <OutputType>Exe</OutputType>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-    <Nullable>enable</Nullable>
-    <ImplicitUsings>enable</ImplicitUsings>
-    <IsPackable>false</IsPackable>
-    <IsAotCompatible>false</IsAotCompatible>
-    <!-- This is a top-level console app; ConfigureAwait is unnecessary -->
-    <NoWarn>$(NoWarn);CA2007</NoWarn>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Azure.AI.OpenAI" />
-    <PackageReference Include="Azure.Identity" />
-    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <ProjectReference Include="..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
-  </ItemGroup>
-
-</Project>

dotnet/samples/02-agents/AgentProviders/Agent_With_Anthropic/README.md

@@ -5,8 +5,8 @@ This sample demonstrates how to create an AIAgent using Anthropic Claude models
 The sample supports three deployment scenarios:
 
 1. **Anthropic Public API** - Direct connection to Anthropic's public API
-2. **Microsoft Foundry with API Key** - Anthropic models deployed through Microsoft Foundry using API key authentication
-3. **Microsoft Foundry with Azure CLI** - Anthropic models deployed through Microsoft Foundry using Azure CLI credentials
+2. **Azure Foundry with API Key** - Anthropic models deployed through Azure Foundry using API key authentication
+3. **Azure Foundry with Azure CLI** - Anthropic models deployed through Azure Foundry using Azure CLI credentials
 
 ## Prerequisites
 
@@ -25,29 +25,29 @@ $env:ANTHROPIC_API_KEY="your-anthropic-api-key"  # Replace with your Anthropic A
 $env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"  # Optional, defaults to claude-haiku-4-5
 ```
 
-### For Microsoft Foundry with API Key
+### For Azure Foundry with API Key
 
-- Microsoft Foundry service endpoint and deployment configured
+- Azure Foundry service endpoint and deployment configured
 - Anthropic API key
 
 Set the following environment variables:
 
 ```powershell
-$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Replace with your Microsoft Foundry resource name (subdomain before .services.ai.azure.com)
+$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Replace with your Azure Foundry resource name (subdomain before .services.ai.azure.com)
 $env:ANTHROPIC_API_KEY="your-anthropic-api-key"  # Replace with your Anthropic API key
 $env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"  # Optional, defaults to claude-haiku-4-5
 ```
 
-### For Microsoft Foundry with Azure CLI
+### For Azure Foundry with Azure CLI
 
-- Microsoft Foundry service endpoint and deployment configured
+- Azure Foundry service endpoint and deployment configured
 - Azure CLI installed and authenticated (for Azure credential authentication)
 
 Set the following environment variables:
 
 ```powershell
-$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Replace with your Microsoft Foundry resource name (subdomain before .services.ai.azure.com)
+$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Replace with your Azure Foundry resource name (subdomain before .services.ai.azure.com)
 $env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"  # Optional, defaults to claude-haiku-4-5
 ```
 
-**Note**: When using Microsoft Foundry with Azure CLI, make sure you're logged in with `az login` and have access to the Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
+**Note**: When using Azure Foundry with Azure CLI, make sure you're logged in with `az login` and have access to the Azure Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureAIAgentsPersistent/Program.cs

@@ -2,7 +2,7 @@
 
 #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 Microsoft Foundry Agents as the backend.
+// This sample shows how to create and use a simple AI agent with Azure Foundry Agents as the backend.
 
 using Azure.AI.Agents.Persistent;
 using Azure.Identity;

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureAIAgentsPersistent/README.md

@@ -13,14 +13,14 @@ Below is a comparison between the classic and new Foundry Agents approaches:
 Before you begin, ensure you have the following prerequisites:
 
 - .NET 10 SDK or later
-- Microsoft Foundry service endpoint and deployment configured
+- Azure Foundry service endpoint and deployment configured
 - Azure CLI installed and authenticated (for Azure credential authentication)
 
-**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
+**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 
 Set the following environment variables:
 
 ```powershell
-$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Microsoft Foundry resource endpoint
+$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Azure Foundry resource endpoint
 $env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"  # Optional, defaults to gpt-4o-mini
 ```

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureAIProject/Program.cs

@@ -1,6 +1,6 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample shows how to create and use AI agents with Microsoft Foundry Agents as the backend.
+// 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;
@@ -13,7 +13,7 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYME
 
 const string JokerName = "JokerAgent";
 
-// Get a client to create/retrieve/delete server side agents with Microsoft Foundry Agents.
+// Get a client to create/retrieve/delete server side agents with Azure Foundry Agents.
 // 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.

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureAIProject/README.md

@@ -13,14 +13,14 @@ Below is a comparison between the classic and new Foundry Agents approaches:
 Before you begin, ensure you have the following prerequisites:
 
 - .NET 10 SDK or later
-- Microsoft Foundry service endpoint and deployment configured
+- Azure Foundry service endpoint and deployment configured
 - Azure CLI installed and authenticated (for Azure credential authentication)
 
-**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
+**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 
 Set the following environment variables:
 
 ```powershell
-$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Microsoft Foundry resource endpoint
+$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Azure Foundry resource endpoint
 $env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"  # Optional, defaults to gpt-4o-mini
 ```

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureFoundryModel/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Microsoft Foundry.
-// You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in your Microsoft Foundry resource.
+// This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Azure AI Foundry.
+// You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in your Azure AI Foundry resource.
 // Note: Ensure that you pick a model that suits your needs. For example, if you want to use function calling, ensure that the model you pick supports function calling.
 
 using System.ClientModel;
@@ -15,7 +15,7 @@ var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? th
 var apiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
 var model = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "Phi-4-mini-instruct";
 
-// Since we are using the OpenAI Client SDK, we need to override the default endpoint to point to Microsoft Foundry.
+// Since we are using the OpenAI Client SDK, we need to override the default endpoint to point to Azure Foundry.
 var clientOptions = new OpenAIClientOptions() { Endpoint = new Uri(endpoint) };
 
 // Create the OpenAI client with either an API key or Azure CLI credential.

dotnet/samples/02-agents/AgentProviders/Agent_With_AzureFoundryModel/README.md

@@ -1,8 +1,8 @@
 ## Overview
 
-This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Microsoft Foundry.
+This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Azure AI Foundry.
 
-You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in Microsoft Foundry.
+You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in Azure AI Foundry.
 
 **Note**: Ensure that you pick a model that suits your needs. For example, if you want to use function calling, ensure that the model you pick supports function calling.
 
@@ -11,19 +11,19 @@ You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI o
 Before you begin, ensure you have the following prerequisites:
 
 - .NET 10 SDK or later
-- Microsoft Foundry resource
-- A model deployment in your Microsoft Foundry resource. This example defaults to using the `Phi-4-mini-instruct` model,
+- Azure AI Foundry resource
+- A model deployment in your Azure AI Foundry resource. This example defaults to using the `Phi-4-mini-instruct` model,
 so if you want to use a different model, ensure that you set your `AZURE_AI_MODEL_DEPLOYMENT_NAME` environment
 variable to the name of your deployed model.
-- An API key or role based authentication to access the Microsoft Foundry resource
+- An API key or role based authentication to access the Azure AI Foundry resource
 
 See [here](https://learn.microsoft.com/en-us/azure/ai-foundry/quickstarts/get-started-code?tabs=csharp) for more info on setting up these prerequisites
 
 Set the following environment variables:
 
 ```powershell
-# Replace with your Microsoft Foundry resource endpoint
-# Ensure that you have the "/openai/v1/" path in the URL, since this is required when using the OpenAI SDK to access Microsoft Foundry models.
+# Replace with your Azure AI Foundry resource endpoint
+# Ensure that you have the "/openai/v1/" path in the URL, since this is required when using the OpenAI SDK to access Azure Foundry models.
 $env:AZURE_OPENAI_ENDPOINT="https://ai-foundry-<myresourcename>.services.ai.azure.com/openai/v1/"
 
 # Optional, defaults to using Azure CLI for authentication if not provided

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

@@ -18,7 +18,7 @@ See the README.md for each sample for the prerequisites for that sample.
 |[Creating an AIAgent with Anthropic](./Agent_With_Anthropic/)|This sample demonstrates how to create an AIAgent using Anthropic Claude models as the underlying inference service|
 |[Creating an AIAgent with Foundry Agents using Azure.AI.Agents.Persistent](./Agent_With_AzureAIAgentsPersistent/)|This sample demonstrates how to create a Foundry Persistent agent and expose it as an AIAgent using the Azure.AI.Agents.Persistent SDK|
 |[Creating an AIAgent with Foundry Agents using Azure.AI.Project](./Agent_With_AzureAIProject/)|This sample demonstrates how to create an Foundry Project agent and expose it as an AIAgent using the Azure.AI.Project SDK|
-|[Creating an AIAgent with Foundry Model](./Agent_With_AzureFoundryModel/)|This sample demonstrates how to use any model deployed to Microsoft Foundry to create an AIAgent|
+|[Creating an AIAgent with AzureFoundry Model](./Agent_With_AzureFoundryModel/)|This sample demonstrates how to use any model deployed to Azure Foundry to create an AIAgent|
 |[Creating an AIAgent with Azure OpenAI ChatCompletion](./Agent_With_AzureOpenAIChatCompletion/)|This sample demonstrates how to create an AIAgent using Azure OpenAI ChatCompletion as the underlying inference service|
 |[Creating an AIAgent with Azure OpenAI Responses](./Agent_With_AzureOpenAIResponses/)|This sample demonstrates how to create an AIAgent using Azure OpenAI Responses as the underlying inference service|
 |[Creating an AIAgent with a custom implementation](./Agent_With_CustomImplementation/)|This sample demonstrates how to create an AIAgent with a custom implementation|

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

@@ -18,9 +18,9 @@ Before you begin, ensure you have the following prerequisites:
 
 **Note**: These samples use Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
 
-## Using Anthropic with Microsoft Foundry
+## Using Anthropic with Azure Foundry
 
-To use Anthropic with Microsoft Foundry, you can check the sample [AgentProviders/Agent_With_Anthropic](../AgentProviders/Agent_With_Anthropic/README.md) for more details.
+To use Anthropic with Azure Foundry, you can check the sample [AgentProviders/Agent_With_Anthropic](../AgentProviders/Agent_With_Anthropic/README.md) for more details.
 
 ## Samples
 

dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/Program.cs

@@ -1,10 +1,10 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 // This sample shows how to use the FoundryMemoryProvider to persist and recall memories for an agent.
-// The sample stores conversation messages in a Microsoft Foundry memory store and retrieves relevant
+// The sample stores conversation messages in an Azure AI Foundry memory store and retrieves relevant
 // memories for subsequent invocations, even across new sessions.
 //
-// Note: Memory extraction in Microsoft Foundry is asynchronous and takes time. This sample demonstrates
+// Note: Memory extraction in Azure AI Foundry is asynchronous and takes time. This sample demonstrates
 // a simple polling approach to wait for memory updates to complete before querying.
 
 using System.Text.Json;
@@ -62,7 +62,7 @@ await memoryProvider.EnsureStoredMemoriesDeletedAsync(session);
 Console.WriteLine(await agent.RunAsync("Hi there! My name is Taylor and I'm planning a hiking trip to Patagonia in November.", session));
 Console.WriteLine(await agent.RunAsync("I'm travelling with my sister and we love finding scenic viewpoints.", session));
 
-// Memory extraction in Microsoft Foundry is asynchronous and takes time to process.
+// Memory extraction in Azure AI Foundry is asynchronous and takes time to process.
 // WhenUpdatesCompletedAsync polls all pending updates and waits for them to complete.
 Console.WriteLine("\nWaiting for Foundry Memory to process updates...");
 await memoryProvider.WhenUpdatesCompletedAsync();

dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/README.md

@@ -1,6 +1,6 @@
-# Agent with Memory Using Microsoft Foundry
+# Agent with Memory Using Azure AI Foundry
 
-This sample demonstrates how to create and run an agent that uses Microsoft Foundry's managed memory service to extract and retrieve individual memories across sessions.
+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 across sessions.
 
 ## Features Demonstrated
 
@@ -13,7 +13,7 @@ This sample demonstrates how to create and run an agent that uses Microsoft Foun
 
 ## Prerequisites
 
-1. Azure subscription with Microsoft Foundry project
+1. Azure subscription with Azure AI Foundry project
 2. Azure OpenAI resource with a chat model deployment (e.g., gpt-4o-mini) and an embedding model deployment (e.g., text-embedding-ada-002)
 3. .NET 10.0 SDK
 4. Azure CLI logged in (`az login`)
@@ -21,7 +21,7 @@ This sample demonstrates how to create and run an agent that uses Microsoft Foun
 ## Environment Variables
 
 ```bash
-# Microsoft Foundry project endpoint and memory store name
+# Azure AI Foundry project endpoint and memory store name
 export AZURE_AI_PROJECT_ENDPOINT="https://your-account.services.ai.azure.com/api/projects/your-project"
 export AZURE_AI_MEMORY_STORE_ID="my_memory_store"
 
@@ -48,10 +48,10 @@ The agent will:
 
 ## Key Differences from Mem0
 
-| Aspect | Mem0 | Microsoft Foundry Memory |
+| Aspect | Mem0 | Azure AI Foundry Memory |
 |--------|------|------------------------|
 | Authentication | API Key | Azure Identity (DefaultAzureCredential) |
 | Scope | ApplicationId, UserId, AgentId, ThreadId | Single `Scope` string |
 | Memory Types | Single memory store | User Profile + Chat Summary |
-| Hosting | Mem0 cloud or self-hosted | Microsoft Foundry managed service |
+| Hosting | Mem0 cloud or self-hosted | Azure AI Foundry managed service |
 | Store Creation | N/A (automatic) | Explicit via `EnsureMemoryStoreCreatedAsync` |

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

@@ -7,7 +7,7 @@ These samples show how to create an agent with the Agent Framework that uses Mem
 |[Chat History memory](./AgentWithMemory_Step01_ChatHistoryMemory/)|This sample demonstrates how to enable an agent to remember messages from previous conversations.|
 |[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 Microsoft Foundry](./AgentWithMemory_Step04_MemoryUsingFoundry/)|This sample demonstrates how to create and run an agent that uses Microsoft Foundry's managed memory service to extract and retrieve individual memories.|
+|[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 Microsoft Foundry agents.
+> **See also**: [Memory Search with Foundry Agents](../AgentsWithFoundry/Agent_Step22_MemorySearch/) - demonstrates using the built-in Memory Search tool with Azure Foundry agents.

dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step02_CustomVectorStoreRAG/README.md

@@ -13,7 +13,7 @@ This sample uses Qdrant for the vector store, but this can easily be swapped out
 - User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource.
 - An existing Qdrant instance. You can use a managed service or run a local instance using Docker, but the sample assumes the instance is running locally.
 
-**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
+**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
 
 **Note**: These samples use Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource and have the `Cognitive Services OpenAI Contributor` role. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 

dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/AgentWithRAG_Step05_Neo4jGraphRAG.csproj

@@ -1,54 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <OutputType>Exe</OutputType>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-
-    <Nullable>enable</Nullable>
-    <ImplicitUsings>enable</ImplicitUsings>
-    <ManagePackageVersionsCentrally>false</ManagePackageVersionsCentrally>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <PackageReference Remove="Microsoft.CodeAnalysis.NetAnalyzers" />
-    <PackageReference Remove="Microsoft.VisualStudio.Threading.Analyzers" />
-    <PackageReference Remove="xunit.analyzers" />
-    <PackageReference Remove="Moq.Analyzers" />
-    <PackageReference Remove="Roslynator.Analyzers" />
-    <PackageReference Remove="Roslynator.CodeAnalysis.Analyzers" />
-    <PackageReference Remove="Roslynator.Formatting.Analyzers" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Azure.AI.OpenAI" Version="2.9.0-beta.1" />
-    <PackageReference Include="Azure.Identity" Version="1.19.0" />
-    <PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-rc4" />
-    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.4.0" />
-    <PackageReference Include="Neo4j.AgentFramework.GraphRAG" Version="0.1.0-preview.2" />
-    <PackageReference Include="Neo4j.Driver" Version="5.28.0" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100">
-      <PrivateAssets>all</PrivateAssets>
-      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
-    </PackageReference>
-    <PackageReference Include="Microsoft.VisualStudio.Threading.Analyzers" Version="17.14.15">
-      <PrivateAssets>all</PrivateAssets>
-      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
-    </PackageReference>
-    <PackageReference Include="Roslynator.Analyzers" Version="4.14.1">
-      <PrivateAssets>all</PrivateAssets>
-      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
-    </PackageReference>
-    <PackageReference Include="Roslynator.CodeAnalysis.Analyzers" Version="4.14.1">
-      <PrivateAssets>all</PrivateAssets>
-      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
-    </PackageReference>
-    <PackageReference Include="Roslynator.Formatting.Analyzers" Version="4.14.1">
-      <PrivateAssets>all</PrivateAssets>
-      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
-    </PackageReference>
-  </ItemGroup>
-
-</Project>

dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/Program.cs

@@ -1,77 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using Azure.AI.OpenAI;
-using Azure.Identity;
-using Microsoft.Agents.AI;
-using Microsoft.Extensions.AI;
-using Neo4j.AgentFramework.GraphRAG;
-using Neo4j.Driver;
-
-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 neo4jUri = Environment.GetEnvironmentVariable("NEO4J_URI") ?? throw new InvalidOperationException("NEO4J_URI is not set.");
-var neo4jUsername = Environment.GetEnvironmentVariable("NEO4J_USERNAME") ?? "neo4j";
-var neo4jPassword = Environment.GetEnvironmentVariable("NEO4J_PASSWORD") ?? throw new InvalidOperationException("NEO4J_PASSWORD is not set.");
-var fulltextIndex = Environment.GetEnvironmentVariable("NEO4J_FULLTEXT_INDEX_NAME") ?? "search_chunks";
-
-const string RetrievalQuery = """
-    MATCH (node)-[:FROM_DOCUMENT]->(doc:Document)<-[:FILED]-(company:Company)
-    OPTIONAL MATCH (company)-[:FACES_RISK]->(risk:RiskFactor)
-    WITH node, score, company, doc, collect(DISTINCT risk.name)[0..5] AS risks
-    OPTIONAL MATCH (company)-[:MENTIONS]->(product:Product)
-    WITH node, score, company, doc, risks, collect(DISTINCT product.name)[0..5] AS products
-    RETURN
-        node.text AS text,
-        score,
-        company.name AS company,
-        company.ticker AS ticker,
-        doc.title AS title,
-        risks,
-        products
-    ORDER BY score DESC
-    """;
-
-await using var driver = GraphDatabase.Driver(new Uri(neo4jUri), AuthTokens.Basic(neo4jUsername, neo4jPassword));
-await driver.VerifyConnectivityAsync();
-
-await using var provider = new Neo4jContextProvider(
-    driver,
-    new Neo4jContextProviderOptions
-    {
-        IndexName = fulltextIndex,
-        IndexType = IndexType.Fulltext,
-        RetrievalQuery = RetrievalQuery,
-        TopK = 5,
-        ContextPrompt = "Use the retrieved Neo4j graph context to answer accurately and call out when context is missing."
-    });
-
-// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
-// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
-// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
-AIAgent agent = new AzureOpenAIClient(
-    new Uri(endpoint),
-    new DefaultAzureCredential())
-    .GetChatClient(deploymentName)
-    .AsIChatClient()
-    .AsAIAgent(new ChatClientAgentOptions
-    {
-        ChatOptions = new()
-        {
-            Instructions = "You are a helpful assistant that answers questions using Neo4j graph context."
-        },
-        AIContextProviders = [provider]
-    });
-
-AgentSession session = await agent.CreateSessionAsync();
-
-foreach (var question in new[]
-{
-    "What products does Microsoft offer?",
-    "What risks does Apple face?",
-    "Tell me about NVIDIA's AI business and risk factors."
-})
-{
-    Console.WriteLine($">> {question}\n");
-    Console.WriteLine(await agent.RunAsync(question, session));
-    Console.WriteLine();
-}

dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/README.md

@@ -1,32 +0,0 @@
-# Agent Framework Retrieval Augmented Generation (RAG) with Neo4j GraphRAG
-
-This sample demonstrates how to create and run an agent that uses the [Neo4j GraphRAG context provider](https://github.com/neo4j-labs/neo4j-maf-provider) with Microsoft Agent Framework for .NET.
-
-The sample uses a Neo4j fulltext index for retrieval and a Cypher `RetrievalQuery` to enrich results with related companies, products, and risk factors.
-
-## Prerequisites
-
-- .NET 10 SDK or later
-- Azure OpenAI endpoint and chat deployment
-- Azure CLI installed and authenticated
-- A Neo4j database with chunked documents and a fulltext index such as `search_chunks`
-
-## Environment variables
-
-```powershell
-$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
-$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"
-$env:NEO4J_URI="neo4j+s://your-instance.databases.neo4j.io"
-$env:NEO4J_USERNAME="neo4j"
-$env:NEO4J_PASSWORD="your-password"
-$env:NEO4J_FULLTEXT_INDEX_NAME="search_chunks"
-```
-
-## Build and run
-
-```powershell
-dotnet build
-dotnet run --framework net10.0 --no-build
-```
-
-The sample issues a few questions against the graph-backed retrieval provider and prints the responses to the console.

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

@@ -8,4 +8,3 @@ These samples show how to create an agent with the Agent Framework that uses Ret
 |[RAG with Vector Store and custom schema](./AgentWithRAG_Step02_CustomVectorStoreRAG/)|This sample demonstrates how to create and run an agent that uses Retrieval Augmented Generation (RAG) with a vector store. It also uses a custom schema for the documents stored in the vector store.|
 |[RAG with custom RAG data source](./AgentWithRAG_Step03_CustomRAGDataSource/)|This sample demonstrates how to create and run an agent that uses Retrieval Augmented Generation (RAG) with a custom RAG data source.|
 |[RAG with Foundry VectorStore service](./AgentWithRAG_Step04_FoundryServiceRAG/)|This sample demonstrates how to create and run an agent that uses Retrieval Augmented Generation (RAG) with the Foundry VectorStore service.|
-|[RAG with Neo4j GraphRAG](./AgentWithRAG_Step05_Neo4jGraphRAG/)|This sample demonstrates how to create and run an agent that uses a Neo4j-backed GraphRAG context provider with graph-enriched retrieval.|

dotnet/samples/02-agents/Agents/Agent_Step02_StructuredOutput/README.md

@@ -18,7 +18,7 @@ Before you begin, ensure you have the following prerequisites:
 - Azure CLI installed and authenticated (for Azure credential authentication)
 - User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource
 
-**Note**: This sample uses Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
+**Note**: This sample uses Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
 
 **Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource and have the `Cognitive Services OpenAI Contributor` role. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 

dotnet/samples/02-agents/Agents/Agent_Step07_AsMcpTool/README.md

@@ -20,8 +20,8 @@ To use the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector)
    MCP Inspector is up and running at http://127.0.0.1:6274
    ```
 1. Open a web browser and navigate to the URL displayed in the terminal. If not opened automatically, this will open the MCP Inspector interface.
-1. In the MCP Inspector interface, add the following environment variables to allow your MCP server to access Microsoft Foundry Project to create and run the agent:
-    - AZURE_AI_PROJECT_ENDPOINT = https://your-resource.openai.azure.com/ # Replace with your Microsoft Foundry Project endpoint
+1. In the MCP Inspector interface, add the following environment variables to allow your MCP server to access Azure AI Foundry Project to create and run the agent:
+    - AZURE_AI_PROJECT_ENDPOINT = https://your-resource.openai.azure.com/ # Replace with your Azure AI Foundry Project endpoint
     - AZURE_AI_MODEL_DEPLOYMENT_NAME = gpt-4o-mini # Replace with your model deployment name
 1. Find and click the `Connect` button in the MCP Inspector interface to connect to the MCP server.
 1. As soon as the connection is established, open the `Tools` tab in the MCP Inspector interface and select the `Joker` tool from the list.

dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/Program.cs

@@ -13,7 +13,7 @@ using Azure.Identity;
 using Microsoft.Agents.AI;
 using Microsoft.Extensions.AI;
 
-// Get Microsoft Foundry configuration from environment variables
+// Get Azure AI Foundry configuration from environment variables
 var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
 var deploymentName = System.Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o";
 

dotnet/samples/02-agents/Agents/Agent_Step13_ChatReduction/Program.cs

@@ -3,7 +3,7 @@
 // This sample shows how to use a chat history reducer to keep the context within model size limits.
 // Any implementation of Microsoft.Extensions.AI.IChatReducer can be used to customize how the chat history is reduced.
 // NOTE: this feature is only supported where the chat history is stored locally, such as with OpenAI Chat Completion.
-// Where the chat history is stored server side, such as with Microsoft Foundry Agents, the service must manage the chat history size.
+// Where the chat history is stored server side, such as with Azure Foundry Agents, the service must manage the chat history size.
 
 using Azure.AI.OpenAI;
 using Azure.Identity;

dotnet/samples/02-agents/Agents/Agent_Step15_DeepResearch/Program.cs

@@ -2,7 +2,7 @@
 
 #pragma warning disable CS0618 // Type or member is obsolete - sample uses deprecated PersistentAgentsClientExtensions
 
-// This sample shows how to create a Microsoft Foundry Agent with the Deep Research Tool.
+// This sample shows how to create an Azure AI Foundry Agent with the Deep Research Tool.
 
 using Azure.AI.Agents.Persistent;
 using Azure.Identity;

dotnet/samples/02-agents/Agents/Agent_Step15_DeepResearch/README.md

@@ -11,10 +11,10 @@ Key features:
 
 Before running this sample, ensure you have:
 
-1. A Microsoft Foundry project set up
+1. An Azure AI Foundry project set up
 2. A deep research model deployment (e.g., o3-deep-research)
 3. A model deployment (e.g., gpt-4o)
-4. A Bing Connection configured in your Microsoft Foundry project
+4. A Bing Connection configured in your Azure AI Foundry project
 5. Azure CLI installed and authenticated
 
 **Important**: Please visit the following documentation for detailed setup instructions:
@@ -29,14 +29,14 @@ Pay special attention to the purple `Note` boxes in the Azure documentation.
 /subscriptions/<sub-id>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<account>/projects/<project>/connections/<connection-name>
 ```
 
-You can find this in the Microsoft Foundry portal under **Management > Connected resources**, or retrieve it programmatically via the connections API (`.id` property).
+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:
 
 ```powershell
-# Replace with your Microsoft Foundry project endpoint
+# 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)

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

@@ -18,7 +18,7 @@ Before you begin, ensure you have the following prerequisites:
 - Azure CLI installed and authenticated (for Azure credential authentication)
 - User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource.
 
-**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
+**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
 
 **Note**: These samples use Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource and have the `Cognitive Services OpenAI Contributor` role. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 

dotnet/samples/02-agents/AgentsWithFoundry/Agent_Step00_FoundryAgentLifecycle/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 // This sample shows how to create, use, and clean up a FoundryAgent backed by a server-side
-// versioned agent in Microsoft Foundry. It demonstrates the full lifecycle:
+// versioned agent in Azure AI Foundry. It demonstrates the full lifecycle:
 // create agent version -> wrap as FoundryAgent -> run -> delete.
 
 using Azure.AI.Projects;

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

@@ -1,6 +1,6 @@
 # Getting started with Foundry Agents
 
-These samples demonstrate how to use Microsoft Foundry with Agent Framework.
+These samples demonstrate how to use Azure AI Foundry with Agent Framework.
 
 ## Quick start
 

dotnet/samples/02-agents/ModelContextProtocol/FoundryAgent_Hosted_MCP/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample shows how to create and use a simple AI agent with Microsoft Foundry Agents as the backend, that uses a Hosted MCP Tool.
-// In this case the Microsoft Foundry Agents service will invoke any MCP tools as required. MCP tools are not invoked by the Agent Framework.
+// This sample shows how to create and use a simple AI agent with Azure Foundry Agents as the backend, that uses a Hosted MCP Tool.
+// In this case the Azure Foundry Agents service will invoke any MCP tools as required. MCP tools are not invoked by the Agent Framework.
 // The sample first shows how to use MCP tools with auto approval, and then how to set up a tool that requires approval before it can be invoked and how to approve such a tool.
 
 using Azure.AI.Projects;

dotnet/samples/02-agents/ModelContextProtocol/FoundryAgent_Hosted_MCP/README.md

@@ -3,14 +3,14 @@
 Before you begin, ensure you have the following prerequisites:
 
 - .NET 10 SDK or later
-- Microsoft Foundry service endpoint and deployment configured
+- Azure Foundry service endpoint and deployment configured
 - Azure CLI installed and authenticated (for Azure credential authentication)
 
-**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
+**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 
 Set the following environment variables:
 
 ```powershell
-$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Microsoft Foundry resource endpoint
+$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Azure Foundry resource endpoint
 $env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4.1-mini"  # Optional, defaults to gpt-4.1-mini
 ```

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

@@ -11,7 +11,7 @@ Before you begin, ensure you have the following prerequisites:
 - Azure CLI installed and authenticated (for Azure credential authentication)
 - User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource.
 
-**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
+**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
 
 **Note**: These samples use Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource and have the `Cognitive Services OpenAI Contributor` role. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
 

dotnet/samples/03-workflows/Agents/FoundryAgent/Program.cs

@@ -11,12 +11,12 @@ using Microsoft.Extensions.AI;
 namespace WorkflowFoundryAgentSample;
 
 /// <summary>
-/// This sample shows how to use Microsoft Foundry Agents within a workflow.
+/// This sample shows how to use Azure Foundry Agents within a workflow.
 /// </summary>
 /// <remarks>
 /// Pre-requisites:
 /// - Foundational samples should be completed first.
-/// - A Microsoft Foundry project endpoint and model ID.
+/// - An Azure Foundry project endpoint and model id.
 /// </remarks>
 public static class Program
 {

dotnet/samples/03-workflows/Declarative/InvokeMcpTool/Program.cs

@@ -30,7 +30,7 @@ namespace Demo.Workflows.Declarative.InvokeMcpTool;
 /// <item>Integrating with MCP-compatible services</item>
 /// </list>
 /// <para>
-/// This sample uses the Microsoft Learn MCP server to search Azure documentation and the Microsoft Foundry MCP server to get AI model details.
+/// This sample uses the Microsoft Learn MCP server to search Azure documentation and the Azure foundry MCP server to get AI model details.
 /// When you run the sample, provide an AI model (e.g. gpt-4.1-mini) as input,
 /// The workflow will use the MCP tools to find relevant information about the model from Microsoft Learn and foundry, then an agent will summarize the results.
 /// </para>

dotnet/samples/03-workflows/Declarative/README.md

@@ -6,7 +6,7 @@ to build a `Workflow` that may be executed using the same pattern as any code-ba
 ## Configuration
 
 These samples must be configured to create and use agents your 
-[Microsoft Foundry Project](https://learn.microsoft.com/azure/ai-foundry).
+[Azure Foundry Project](https://learn.microsoft.com/azure/ai-foundry).
 
 ### Settings
 
@@ -18,9 +18,9 @@ The configuraton required by the samples is:
 
 |Setting Name| Description|
 |:--|:--|
-|AZURE_AI_PROJECT_ENDPOINT| The endpoint URL of your Microsoft Foundry Project.|
+|AZURE_AI_PROJECT_ENDPOINT| The endpoint URL of your Azure Foundry Project.|
 |AZURE_AI_MODEL_DEPLOYMENT_NAME| The name of the model deployment to use
-|AZURE_AI_BING_CONNECTION_ID| The name of the Bing Grounding connection configured in your Microsoft Foundry Project.|
+|AZURE_AI_BING_CONNECTION_ID| The name of the Bing Grounding connection configured in your Azure Foundry Project.|
 
 To set your secrets with .NET Secret Manager:
 
@@ -42,13 +42,13 @@ To set your secrets with .NET Secret Manager:
     dotnet user-secrets init
     ```
 
-4. Define setting that identifies your Microsoft Foundry Project (endpoint):
+4. Define setting that identifies your Azure Foundry Project (endpoint):
 
     ```
     dotnet user-secrets set "AZURE_AI_PROJECT_ENDPOINT" "https://..."
     ```
 
-5. Define setting that identifies your Microsoft Foundry Model Deployment (endpoint):
+5. Define setting that identifies your Azure Foundry Model Deployment (endpoint):
 
     ```
     dotnet user-secrets set "AZURE_AI_MODEL_DEPLOYMENT_NAME" "gpt-5"
@@ -70,7 +70,7 @@ $env:AZURE_AI_BING_CONNECTION_ID="mybinggrounding"
 
 ### Authorization
 
-Use [_Azure CLI_](https://learn.microsoft.com/cli/azure/authenticate-azure-cli) to authorize access to your Microsoft Foundry Project:
+Use [_Azure CLI_](https://learn.microsoft.com/cli/azure/authenticate-azure-cli) to authorize access to your Azure Foundry Project:
 
 ```
 az login

dotnet/samples/03-workflows/README.md

@@ -26,7 +26,7 @@ Once completed, please proceed to the other samples listed below.
 
 | Sample | Concepts |
 |--------|----------|
-| [Foundry Agents in Workflows](./Agents/FoundryAgent) | Demonstrates using Microsoft Foundry agents in a workflow through `ChatClientAgent` |
+| [Foundry Agents in Workflows](./Agents/FoundryAgent) | Demonstrates using Azure Foundry agents in a workflow through `ChatClientAgent` |
 | [Custom Agent Executors](./Agents/CustomAgentExecutors) | Shows how to create a custom agent executor for more complex scenarios |
 | [Workflow as an Agent](./Agents/WorkflowAsAnAgent) | Illustrates how to encapsulate a workflow as an agent |
 | [Group Chat with Tool Approval](./Agents/GroupChatToolApproval) | Shows multi-agent group chat with tool approval requests and human-in-the-loop interaction |

dotnet/samples/05-end-to-end/A2AClientServer/README.md

@@ -51,7 +51,7 @@ dotnet run --urls "http://localhost:5002;https://localhost:5012" --agentType "lo
 
 ### Configuring for use with Azure AI Agents
 
-You must create the agents in a Microsoft Foundry project and then provide the project endpoint and agent IDs. The instructions for each agent are as follows:
+You must create the agents in an Azure AI Foundry project and then provide the project endpoint and agents ids. The instructions for each agent are as follows:
 
 - Invoice Agent
     ```

dotnet/samples/05-end-to-end/HostedAgents/AgentWithLocalTools/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 // Seattle Hotel Agent - A simple agent with a tool to find hotels in Seattle.
-// Uses Microsoft Agent Framework with Microsoft Foundry.
+// Uses Microsoft Agent Framework with Azure AI Foundry.
 // Ready for deployment to Foundry Hosted Agent service.
 
 using System.ClientModel.Primitives;

dotnet/samples/05-end-to-end/HostedAgents/AgentWithLocalTools/README.md

@@ -4,7 +4,7 @@ This sample demonstrates how to build a hosted agent that uses local C# function
 
 Key features:
 - Defining local C# functions as agent tools using `AIFunctionFactory`
-- Using `AIProjectClient` to discover the OpenAI connection from the Microsoft Foundry project
+- Using `AIProjectClient` to discover the OpenAI connection from the Azure AI Foundry project
 - Building a `ChatClientAgent` with custom instructions and tools
 - Deploying to the Foundry Hosted Agent service
 
@@ -15,7 +15,7 @@ Key features:
 Before running this sample, ensure you have:
 
 1. .NET 10 SDK installed
-2. A Microsoft Foundry Project with a chat model deployed (e.g., gpt-4o-mini)
+2. An Azure AI Foundry Project with a chat model deployed (e.g., gpt-4o-mini)
 3. Azure CLI installed and authenticated (`az login`)
 
 ## Environment Variables
@@ -23,7 +23,7 @@ Before running this sample, ensure you have:
 Set the following environment variables:
 
 ```powershell
-# Replace with your Microsoft Foundry project endpoint
+# Replace with your Azure AI Foundry project endpoint
 $env:AZURE_AI_PROJECT_ENDPOINT="https://your-project.services.ai.azure.com/api/projects/your-project-name"
 
 # Optional, defaults to gpt-4o-mini

dotnet/samples/05-end-to-end/HostedAgents/FoundryMultiAgent/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 // This sample demonstrates a multi-agent workflow with Writer and Reviewer agents
-// using Microsoft Foundry AIProjectClient and the Agent Framework WorkflowBuilder.
+// using Azure AI Foundry AIProjectClient and the Agent Framework WorkflowBuilder.
 
 #pragma warning disable CA2252 // AIProjectClient and Agents API require opting into preview features
 

dotnet/samples/05-end-to-end/HostedAgents/FoundryMultiAgent/README.md

@@ -42,7 +42,7 @@ which provisions a REST API endpoint compatible with the OpenAI Responses protoc
 
 Before running this sample, ensure you have:
 
-1. **Microsoft Foundry Project**
+1. **Azure AI Foundry Project**
    - Project created.
    - Chat model deployed (e.g., `gpt-4o` or `gpt-4.1`)
    - Note your project endpoint URL and model deployment name

dotnet/samples/05-end-to-end/HostedAgents/FoundryMultiAgent/agent.yaml

@@ -4,7 +4,7 @@ name: FoundryMultiAgent
 displayName: "Foundry Multi-Agent Workflow"
 description: >
   A multi-agent workflow featuring a Writer and Reviewer that collaborate
-  to create and refine content using Microsoft Foundry PersistentAgentsClient.
+  to create and refine content using Azure AI Foundry PersistentAgentsClient.
 metadata:
   authors:
     - Microsoft Agent Framework Team

dotnet/samples/05-end-to-end/HostedAgents/FoundrySingleAgent/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 // Seattle Hotel Agent - A simple agent with a tool to find hotels in Seattle.
-// Uses Microsoft Agent Framework with Microsoft Foundry.
+// Uses Microsoft Agent Framework with Azure AI Foundry.
 // Ready for deployment to Foundry Hosted Agent service.
 
 #pragma warning disable CA2252 // AIProjectClient and Agents API require opting into preview features

dotnet/samples/05-end-to-end/HostedAgents/FoundrySingleAgent/README.md

@@ -39,7 +39,7 @@ which provisions a REST API endpoint compatible with the OpenAI Responses protoc
 
 Before running this sample, ensure you have:
 
-1. **Microsoft Foundry Project**
+1. **Azure AI Foundry Project**
    - Project created.
    - Chat model deployed (e.g., `gpt-4o` or `gpt-4.1`)
    - Note your project endpoint URL and model deployment name
@@ -57,7 +57,7 @@ Before running this sample, ensure you have:
 
 Set the following environment variables (matching `agent.yaml`):
 
-- `AZURE_AI_PROJECT_ENDPOINT` - Your Microsoft Foundry project endpoint URL (required)
+- `AZURE_AI_PROJECT_ENDPOINT` - Your Azure AI Foundry project endpoint URL (required)
 - `MODEL_DEPLOYMENT_NAME` - The deployment name for your chat model (defaults to `gpt-4o-mini`)
 
 **PowerShell:**

dotnet/samples/05-end-to-end/HostedAgents/README.md

@@ -20,7 +20,7 @@ Before running any sample, ensure you have:
 
 1. **.NET 10 SDK** or later — [Download](https://dotnet.microsoft.com/download/dotnet/10.0)
 2. **Azure CLI** installed — [Install guide](https://learn.microsoft.com/cli/azure/install-azure-cli)
-3. **Azure OpenAI** or **Microsoft Foundry project** with a chat model deployed (e.g., `gpt-4o-mini`)
+3. **Azure OpenAI** or **Azure AI Foundry project** with a chat model deployed (e.g., `gpt-4o-mini`)
 
 ### Authenticate with Azure CLI
 
@@ -39,14 +39,14 @@ Most samples require one or more of these environment variables:
 |----------|---------|-------------|
 | `AZURE_OPENAI_ENDPOINT` | Most samples | Your Azure OpenAI resource endpoint URL |
 | `AZURE_OPENAI_DEPLOYMENT_NAME` | Most samples | Chat model deployment name (defaults to `gpt-4o-mini`) |
-| `AZURE_AI_PROJECT_ENDPOINT` | AgentWithLocalTools, FoundryMultiAgent, FoundrySingleAgent | Microsoft Foundry project endpoint |
+| `AZURE_AI_PROJECT_ENDPOINT` | AgentWithLocalTools, FoundryMultiAgent, FoundrySingleAgent | Azure AI Foundry project endpoint |
 | `MODEL_DEPLOYMENT_NAME` | AgentWithLocalTools, FoundryMultiAgent, FoundrySingleAgent | Chat model deployment name (defaults to `gpt-4o-mini`) |
 
 See each sample's README for the specific variables required.
 
-## Microsoft Foundry Setup (for samples that use Foundry)
+## Azure AI Foundry Setup (for samples that use Foundry)
 
-Some samples (`AgentWithLocalTools`, `FoundrySingleAgent`, `FoundryMultiAgent`) connect to a Microsoft Foundry project. If you're using these samples, you'll need additional setup.
+Some samples (`AgentWithLocalTools`, `FoundrySingleAgent`, `FoundryMultiAgent`) connect to an Azure AI Foundry project. If you're using these samples, you'll need additional setup.
 
 ### Azure AI Developer Role
 
@@ -61,7 +61,7 @@ az role assignment create `
 
 > **Note**: You need **Owner** or **User Access Administrator** permissions on the resource to assign roles. If you don't have this, you may need to request JIT (Just-In-Time) elevated access via [Azure PIM](https://portal.azure.com/#view/Microsoft_Azure_PIMCommon/ActivationMenuBlade/~/aadmigratedresource).
 
-For more details on permissions, see [Microsoft Foundry Permissions](https://aka.ms/FoundryPermissions).
+For more details on permissions, see [Azure AI Foundry Permissions](https://aka.ms/FoundryPermissions).
 
 ## Running a Sample
 

dotnet/samples/AGENTS.md

@@ -28,7 +28,7 @@ dotnet/samples/
 │   ├── AGUI/                          # AG-UI protocol samples
 │   ├── DeclarativeAgents/             # Declarative agent definitions
 │   ├── DevUI/                         # DevUI samples
-│   ├── AgentsWithFoundry/             # Microsoft Foundry samples (FoundryAgent + AsAIAgent extensions)
+│   ├── AgentsWithFoundry/             # Azure AI Foundry samples (FoundryAgent + AsAIAgent extensions)
 │   └── ModelContextProtocol/          # MCP server/client patterns
 ├── 03-workflows/                      # Workflow patterns
 │   ├── _StartHere/                    # Introductory workflow samples

dotnet/src/Microsoft.Agents.AI.Workflows/Checkpointing/ICheckpointingHandle.cs

@@ -21,15 +21,6 @@ internal interface ICheckpointingHandle
     /// <summary>
     /// Restores the system state from the specified checkpoint asynchronously.
     /// </summary>
-    /// <remarks>
-    /// This contract is used by live runtime restore paths. Implementations may re-emit pending
-    /// external request events as part of the restore once the active event stream is ready to
-    /// observe them.
-    ///
-    /// Initial resume paths that create a new event stream should restore state first and defer
-    /// any replay until after the subscriber is attached, rather than calling this contract
-    /// directly before the stream is ready.
-    /// </remarks>
     /// <param name="checkpointInfo">The checkpoint information that identifies the state to restore. Cannot be null.</param>
     /// <param name="cancellationToken">A cancellation token that can be used to cancel the restore operation.</param>
     /// <returns>A <see cref="ValueTask"/> that represents the asynchronous restore operation.</returns>

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

@@ -36,10 +36,9 @@ internal sealed class AsyncRunHandle : ICheckpointingHandle, IAsyncDisposable
 
         this._eventStream.Start();
 
-        // If there are already unprocessed messages or unserviced requests (e.g., from a
-        // checkpoint restore that happened before this handle was created), signal the run
-        // loop to start processing them
-        if (stepRunner.HasUnprocessedMessages || stepRunner.HasUnservicedRequests)
+        // If there are already unprocessed messages (e.g., from a checkpoint restore that happened
+        // before this handle was created), signal the run loop to start processing them
+        if (stepRunner.HasUnprocessedMessages)
         {
             this.SignalInputToRunLoop();
         }
@@ -193,17 +192,13 @@ internal sealed class AsyncRunHandle : ICheckpointingHandle, IAsyncDisposable
         {
             streamingEventStream.ClearBufferedEvents();
         }
-        else if (this._eventStream is LockstepRunEventStream lockstepEventStream)
-        {
-            lockstepEventStream.ClearBufferedEvents();
-        }
 
-        // Restore the workflow state through the live runtime-restore path.
-        // This can re-emit pending requests into the already-active event stream.
+        // Restore the workflow state - this will republish unserviced requests as new events
         await this._checkpointingHandle.RestoreCheckpointAsync(checkpointInfo, cancellationToken).ConfigureAwait(false);
 
-        // After restore, signal the run loop to process any restored messages. Initial resume
-        // paths handle this separately when they create the event stream after restoring state.
+        // After restore, signal the run loop to process any restored messages
+        // This is necessary because ClearBufferedEvents() doesn't signal, and the restored
+        // queued messages won't automatically wake up the run loop
         this.SignalInputToRunLoop();
     }
 }

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

@@ -27,14 +27,6 @@ internal interface ISuperStepRunner
 
     ConcurrentEventSink OutgoingEvents { get; }
 
-    /// <summary>
-    /// Re-emits <see cref="RequestInfoEvent"/>s for any pending external requests.
-    /// Called by event streams after subscribing to <see cref="OutgoingEvents"/> so that
-    /// requests restored from a checkpoint are observable even when the restore happened
-    /// before the subscription was active.
-    /// </summary>
-    ValueTask RepublishPendingEventsAsync(CancellationToken cancellationToken = default);
-
     ValueTask<bool> RunSuperStepAsync(CancellationToken cancellationToken);
 
     // This cannot be cancelled

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

@@ -15,7 +15,6 @@ internal sealed class LockstepRunEventStream : IRunEventStream
 {
     private readonly CancellationTokenSource _stopCancellation = new();
     private readonly InputWaiter _inputWaiter = new();
-    private ConcurrentQueue<WorkflowEvent> _eventSink = new();
     private int _isDisposed;
 
     private readonly ISuperStepRunner _stepRunner;
@@ -36,8 +35,6 @@ internal sealed class LockstepRunEventStream : IRunEventStream
         // doesn't leak into caller code via AsyncLocal.
         Activity? previousActivity = Activity.Current;
 
-        this._stepRunner.OutgoingEvents.EventRaised += this.OnWorkflowEventAsync;
-
         this._sessionActivity = this._stepRunner.TelemetryContext.StartWorkflowSessionActivity();
         this._sessionActivity?.SetTag(Tags.WorkflowId, this._stepRunner.StartExecutorId)
                               .SetTag(Tags.SessionId, this._stepRunner.SessionId);
@@ -59,6 +56,10 @@ internal sealed class LockstepRunEventStream : IRunEventStream
 
         using CancellationTokenSource linkedSource = CancellationTokenSource.CreateLinkedTokenSource(this._stopCancellation.Token, cancellationToken);
 
+        ConcurrentQueue<WorkflowEvent> eventSink = [];
+
+        this._stepRunner.OutgoingEvents.EventRaised += OnWorkflowEventAsync;
+
         // Re-establish session as parent so the run activity nests correctly.
         Activity.Current = this._sessionActivity;
 
@@ -72,31 +73,7 @@ internal sealed class LockstepRunEventStream : IRunEventStream
             runActivity?.AddEvent(new ActivityEvent(EventNames.WorkflowStarted));
 
             // Emit WorkflowStartedEvent to the event stream for consumers
-            this._eventSink.Enqueue(new WorkflowStartedEvent());
-
-            // Re-emit any pending external requests that were restored from a checkpoint
-            // before this subscription was active. For non-resume starts this is a no-op.
-            // This runs after WorkflowStartedEvent so consumers always see the started event first.
-            await this._stepRunner.RepublishPendingEventsAsync(linkedSource.Token).ConfigureAwait(false);
-
-            // When resuming from a checkpoint with only pending requests (no queued messages),
-            // the inner processing loop won't execute, so we must drain events now.
-            // For normal starts this is a no-op since the inner loop handles the drain.
-            if (!this._stepRunner.HasUnprocessedMessages)
-            {
-                var (drainedEvents, shouldHalt) = this.DrainAndFilterEvents();
-                foreach (WorkflowEvent raisedEvent in drainedEvents)
-                {
-                    yield return raisedEvent;
-                }
-
-                if (shouldHalt)
-                {
-                    yield break;
-                }
-
-                this.RunStatus = this._stepRunner.HasUnservicedRequests ? RunStatus.PendingRequests : RunStatus.Idle;
-            }
+            eventSink.Enqueue(new WorkflowStartedEvent());
 
             do
             {
@@ -130,19 +107,26 @@ internal sealed class LockstepRunEventStream : IRunEventStream
                         yield break; // Exit if cancellation is requested
                     }
 
-                    var (drainedEvents, shouldHalt) = this.DrainAndFilterEvents();
-
-                    foreach (WorkflowEvent raisedEvent in drainedEvents)
+                    bool hadRequestHaltEvent = false;
+                    foreach (WorkflowEvent raisedEvent in Interlocked.Exchange(ref eventSink, []))
                     {
                         if (linkedSource.Token.IsCancellationRequested)
                         {
                             yield break; // Exit if cancellation is requested
                         }
 
-                        yield return raisedEvent;
+                        // TODO: Do we actually want to interpret this as a termination request?
+                        if (raisedEvent is RequestHaltEvent)
+                        {
+                            hadRequestHaltEvent = true;
+                        }
+                        else
+                        {
+                            yield return raisedEvent;
+                        }
                     }
 
-                    if (shouldHalt || linkedSource.Token.IsCancellationRequested)
+                    if (hadRequestHaltEvent || linkedSource.Token.IsCancellationRequested)
                     {
                         // If we had a completion event, we are done.
                         yield break;
@@ -167,23 +151,25 @@ internal sealed class LockstepRunEventStream : IRunEventStream
         finally
         {
             this.RunStatus = this._stepRunner.HasUnservicedRequests ? RunStatus.PendingRequests : RunStatus.Idle;
+            this._stepRunner.OutgoingEvents.EventRaised -= OnWorkflowEventAsync;
 
             // Explicitly dispose the Activity so Activity.Stop fires deterministically,
             // regardless of how the async iterator enumerator is disposed.
             runActivity?.Dispose();
         }
 
+        ValueTask OnWorkflowEventAsync(object? sender, WorkflowEvent e)
+        {
+            eventSink.Enqueue(e);
+            return default;
+        }
+
         // If we are Idle or Ended, we should break out of the loop
         // If we are PendingRequests and not blocking on pending requests, we should break out of the loop
         // If cancellation is requested, we should break out of the loop
         bool ShouldBreak() => this.RunStatus is RunStatus.Idle or RunStatus.Ended ||
-                               (this.RunStatus == RunStatus.PendingRequests && !blockOnPendingRequest) ||
-                               linkedSource.Token.IsCancellationRequested;
-    }
-
-    internal void ClearBufferedEvents()
-    {
-        Interlocked.Exchange(ref this._eventSink, new ConcurrentQueue<WorkflowEvent>());
+                              (this.RunStatus == RunStatus.PendingRequests && !blockOnPendingRequest) ||
+                              linkedSource.Token.IsCancellationRequested;
     }
 
     /// <summary>
@@ -206,7 +192,6 @@ internal sealed class LockstepRunEventStream : IRunEventStream
         if (Interlocked.Exchange(ref this._isDisposed, 1) == 0)
         {
             this._stopCancellation.Cancel();
-            this._stepRunner.OutgoingEvents.EventRaised -= this.OnWorkflowEventAsync;
 
             // Stop the session activity
             if (this._sessionActivity is not null)
@@ -222,32 +207,4 @@ internal sealed class LockstepRunEventStream : IRunEventStream
 
         return default;
     }
-
-    private ValueTask OnWorkflowEventAsync(object? sender, WorkflowEvent e)
-    {
-        this._eventSink.Enqueue(e);
-        return default;
-    }
-
-    // Atomically drains the event sink and separates workflow events from halt signals.
-    // Used by both the early-drain (resume with pending requests only) and
-    // the inner superstep drain to keep halt-detection logic in one place.
-    private (List<WorkflowEvent> Events, bool ShouldHalt) DrainAndFilterEvents()
-    {
-        List<WorkflowEvent> events = [];
-        bool shouldHalt = false;
-        foreach (WorkflowEvent e in Interlocked.Exchange(ref this._eventSink, new ConcurrentQueue<WorkflowEvent>()))
-        {
-            if (e is RequestHaltEvent)
-            {
-                shouldHalt = true;
-            }
-            else
-            {
-                events.Add(e);
-            }
-        }
-
-        return (events, shouldHalt);
-    }
 }

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

@@ -23,8 +23,7 @@ internal sealed class StreamingRunEventStream : IRunEventStream
     private readonly CancellationTokenSource _runLoopCancellation;
     private readonly bool _disableRunLoop;
     private Task? _runLoopTask;
-    private volatile RunStatus _runStatus = RunStatus.NotStarted;
-
+    private RunStatus _runStatus = RunStatus.NotStarted;
     private int _completionEpoch; // Tracks which completion signal belongs to which consumer iteration
 
     public StreamingRunEventStream(ISuperStepRunner stepRunner, bool disableRunLoop = false)
@@ -61,10 +60,6 @@ internal sealed class StreamingRunEventStream : IRunEventStream
         // Subscribe to events - they will flow directly to the channel as they're raised
         this._stepRunner.OutgoingEvents.EventRaised += OnEventRaisedAsync;
 
-        // Re-emit any pending external requests that were restored from a checkpoint
-        // before this subscription was active. For non-resume starts this is a no-op.
-        await this._stepRunner.RepublishPendingEventsAsync(linkedSource.Token).ConfigureAwait(false);
-
         // Start the session-level activity that spans the entire run loop lifetime.
         // Individual run-stage activities are nested within this session activity.
         Activity? sessionActivity = this._stepRunner.TelemetryContext.StartWorkflowSessionActivity();
@@ -128,7 +123,7 @@ internal sealed class StreamingRunEventStream : IRunEventStream
 
                 // Wait for next input from the consumer
                 // Works for both Idle (no work) and PendingRequests (waiting for responses)
-                await this._inputWaiter.WaitForInputAsync(linkedSource.Token).ConfigureAwait(false);
+                await this._inputWaiter.WaitForInputAsync(TimeSpan.FromSeconds(1), linkedSource.Token).ConfigureAwait(false);
 
                 // When signaled, resume running
                 this._runStatus = RunStatus.Running;
@@ -210,10 +205,7 @@ internal sealed class StreamingRunEventStream : IRunEventStream
         [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {
         // Get the current epoch - we'll only respond to completion signals from this epoch or later
-        int currentEpoch = Volatile.Read(ref this._completionEpoch);
-
-        bool expectingFreshWork = this._stepRunner.HasUnprocessedMessages || this._runStatus == RunStatus.Running;
-        int myEpoch = expectingFreshWork ? currentEpoch + 1 : currentEpoch;
+        int myEpoch = Volatile.Read(ref this._completionEpoch) + 1;
 
         // Use custom async enumerable to avoid exceptions on cancellation.
         NonThrowingChannelReaderAsyncEnumerable<WorkflowEvent> eventStream = new(this._eventChannel.Reader);

dotnet/src/Microsoft.Agents.AI.Workflows/InProc/InProcessExecutionEnvironment.cs

@@ -50,13 +50,10 @@ public sealed class InProcessExecutionEnvironment : IWorkflowExecutionEnvironmen
         return runner.BeginStreamAsync(this.ExecutionMode, cancellationToken);
     }
 
-    internal ValueTask<AsyncRunHandle> ResumeRunAsync(Workflow workflow, CheckpointInfo fromCheckpoint, IEnumerable<Type> knownValidInputTypes, CancellationToken cancellationToken = default)
-        => this.ResumeRunAsync(workflow, fromCheckpoint, knownValidInputTypes, republishPendingEvents: true, cancellationToken);
-
-    internal ValueTask<AsyncRunHandle> ResumeRunAsync(Workflow workflow, CheckpointInfo fromCheckpoint, IEnumerable<Type> knownValidInputTypes, bool republishPendingEvents, CancellationToken cancellationToken = default)
+    internal ValueTask<AsyncRunHandle> ResumeRunAsync(Workflow workflow, CheckpointInfo fromCheckpoint, IEnumerable<Type> knownValidInputTypes, CancellationToken cancellationToken)
     {
         InProcessRunner runner = InProcessRunner.CreateTopLevelRunner(workflow, this.CheckpointManager, fromCheckpoint.SessionId, this.EnableConcurrentRuns, knownValidInputTypes);
-        return runner.ResumeStreamAsync(this.ExecutionMode, fromCheckpoint, republishPendingEvents, cancellationToken);
+        return runner.ResumeStreamAsync(this.ExecutionMode, fromCheckpoint, cancellationToken);
     }
 
     /// <inheritdoc/>
@@ -107,32 +104,6 @@ public sealed class InProcessExecutionEnvironment : IWorkflowExecutionEnvironmen
         return new(runHandle);
     }
 
-    /// <summary>
-    /// Resumes a streaming workflow run from a checkpoint with control over whether
-    /// pending request events are republished through the event stream.
-    /// </summary>
-    /// <param name="workflow">The workflow to resume.</param>
-    /// <param name="fromCheckpoint">The checkpoint to resume from.</param>
-    /// <param name="republishPendingEvents">
-    /// When <see langword="true"/>, any pending request events are republished through the event
-    /// stream after subscribing. When <see langword="false"/>, the caller is responsible for
-    /// handling pending requests (e.g., <see cref="WorkflowSession"/> already sends responses).
-    /// </param>
-    /// <param name="cancellationToken">Cancellation token.</param>
-    internal async ValueTask<StreamingRun> ResumeStreamingInternalAsync(
-        Workflow workflow,
-        CheckpointInfo fromCheckpoint,
-        bool republishPendingEvents,
-        CancellationToken cancellationToken = default)
-    {
-        this.VerifyCheckpointingConfigured();
-
-        AsyncRunHandle runHandle = await this.ResumeRunAsync(workflow, fromCheckpoint, [], republishPendingEvents, cancellationToken)
-                                             .ConfigureAwait(false);
-
-        return new(runHandle);
-    }
-
     private async ValueTask<AsyncRunHandle> BeginRunHandlingChatProtocolAsync<TInput>(Workflow workflow,
         TInput input,
         string? sessionId = null,

dotnet/src/Microsoft.Agents.AI.Workflows/InProc/InProcessRunner.cs

@@ -71,28 +71,6 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
     /// <inheritdoc cref="ISuperStepRunner.StartExecutorId"/>
     public string StartExecutorId { get; }
 
-    /// <summary>
-    /// Gating flag for deferred event republishing after checkpoint restore.
-    /// </summary>
-    /// <remarks>
-    /// <para>
-    /// Written with <see cref="Volatile.Write(ref int, int)"/> in <see cref="ResumeStreamAsync(ExecutionMode, CheckpointInfo, bool, CancellationToken)"/>
-    /// and consumed atomically with <see cref="Interlocked.Exchange(ref int, int)"/> in
-    /// <see cref="ISuperStepRunner.RepublishPendingEventsAsync"/>. The write does not need a full
-    /// memory barrier because it is sequenced before the <see cref="AsyncRunHandle"/> constructor
-    /// by the <see langword="await"/> in <see cref="ResumeStreamAsync(ExecutionMode, CheckpointInfo, bool, CancellationToken)"/>. The constructor is the
-    /// only code path that triggers consumption (via the event stream's subscribe and republish flow).
-    /// </para>
-    /// <para>
-    /// Note: <see cref="AsyncRunHandle"/> also reads <see cref="ISuperStepRunner.HasUnservicedRequests"/>
-    /// in its constructor to signal the run loop, but that property reads from
-    /// <see cref="InProcessRunnerContext"/>'s request dictionary (restored during
-    /// <see cref="RestoreCheckpointCoreAsync"/>), not from this flag. The two are independent:
-    /// <c>HasUnservicedRequests</c> triggers the run loop; <c>_needsRepublish</c> triggers event emission.
-    /// </para>
-    /// </remarks>
-    private int _needsRepublish;
-
     /// <inheritdoc cref="ISuperStepRunner.TelemetryContext"/>
     public WorkflowTelemetryContext TelemetryContext => this.Workflow.TelemetryContext;
 
@@ -167,10 +145,7 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
         return new(new AsyncRunHandle(this, this, mode));
     }
 
-    public ValueTask<AsyncRunHandle> ResumeStreamAsync(ExecutionMode mode, CheckpointInfo fromCheckpoint, CancellationToken cancellationToken = default)
-        => this.ResumeStreamAsync(mode, fromCheckpoint, republishPendingEvents: true, cancellationToken);
-
-    public async ValueTask<AsyncRunHandle> ResumeStreamAsync(ExecutionMode mode, CheckpointInfo fromCheckpoint, bool republishPendingEvents, CancellationToken cancellationToken = default)
+    public async ValueTask<AsyncRunHandle> ResumeStreamAsync(ExecutionMode mode, CheckpointInfo fromCheckpoint, CancellationToken cancellationToken = default)
     {
         this.RunContext.CheckEnded();
         Throw.IfNull(fromCheckpoint);
@@ -179,18 +154,7 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
             throw new InvalidOperationException("This runner was not configured with a CheckpointManager, so it cannot restore checkpoints.");
         }
 
-        // Restore checkpoint state without republishing pending request events.
-        // The event stream will republish them after subscribing so that events
-        // are never lost to an absent subscriber.
-        await this.RestoreCheckpointCoreAsync(fromCheckpoint, cancellationToken).ConfigureAwait(false);
-
-        if (republishPendingEvents)
-        {
-            // Signal the event stream to republish pending requests after subscribing.
-            // This is consumed atomically by RepublishPendingEventsAsync.
-            Volatile.Write(ref this._needsRepublish, 1);
-        }
-
+        await this.RestoreCheckpointAsync(fromCheckpoint, cancellationToken).ConfigureAwait(false);
         return new AsyncRunHandle(this, this, mode);
     }
 
@@ -199,16 +163,6 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
     bool ISuperStepRunner.TryGetResponsePortExecutorId(string portId, out string? executorId)
         => this.RunContext.TryGetResponsePortExecutorId(portId, out executorId);
 
-    ValueTask ISuperStepRunner.RepublishPendingEventsAsync(CancellationToken cancellationToken)
-    {
-        if (Interlocked.Exchange(ref this._needsRepublish, 0) != 0)
-        {
-            return this.RunContext.RepublishUnservicedRequestsAsync(cancellationToken);
-        }
-
-        return default;
-    }
-
     public bool IsCheckpointingEnabled => this.RunContext.IsCheckpointingEnabled;
 
     public IReadOnlyList<CheckpointInfo> Checkpoints => this._checkpoints;
@@ -356,31 +310,7 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
         this._checkpoints.Add(this._lastCheckpointInfo);
     }
 
-    /// <summary>
-    /// Restores checkpoint state and re-emits any pending external request events.
-    /// </summary>
-    /// <remarks>
-    /// This is the <see cref="ICheckpointingHandle"/> implementation used for runtime restores
-    /// where the event stream subscription is already active. For initial resumes,
-    /// <see cref="ResumeStreamAsync(ExecutionMode, CheckpointInfo, CancellationToken)"/> calls
-    /// <see cref="RestoreCheckpointCoreAsync"/> directly and defers republishing to the event stream.
-    /// </remarks>
     public async ValueTask RestoreCheckpointAsync(CheckpointInfo checkpointInfo, CancellationToken cancellationToken = default)
-    {
-        await this.RestoreCheckpointCoreAsync(checkpointInfo, cancellationToken).ConfigureAwait(false);
-
-        // Republish pending request events. This is safe for runtime restores where
-        // the event stream is already subscribed. For initial resumes the event stream
-        // handles republishing itself, so ResumeStreamAsync calls RestoreCheckpointCoreAsync directly.
-        await this.RunContext.RepublishUnservicedRequestsAsync(cancellationToken).ConfigureAwait(false);
-    }
-
-    /// <summary>
-    /// Restores checkpoint state (queued messages, executor state, edge state, etc.)
-    /// without republishing pending request events. The caller is responsible for
-    /// ensuring events are republished after an event subscriber is attached.
-    /// </summary>
-    private async ValueTask RestoreCheckpointCoreAsync(CheckpointInfo checkpointInfo, CancellationToken cancellationToken = default)
     {
         this.RunContext.CheckEnded();
         Throw.IfNull(checkpointInfo);
@@ -405,9 +335,11 @@ internal sealed class InProcessRunner : ISuperStepRunner, ICheckpointingHandle
         await this.RunContext.ImportStateAsync(checkpoint).ConfigureAwait(false);
 
         Task executorNotifyTask = this.RunContext.NotifyCheckpointLoadedAsync(cancellationToken);
+        ValueTask republishRequestsTask = this.RunContext.RepublishUnservicedRequestsAsync(cancellationToken);
 
         await this.EdgeMap.ImportStateAsync(checkpoint).ConfigureAwait(false);
         await Task.WhenAll(executorNotifyTask,
+                           republishRequestsTask.AsTask(),
                            restoreCheckpointIndexTask.AsTask()).ConfigureAwait(false);
 
         this._lastCheckpointInfo = checkpointInfo;

dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/RequestInfoExecutor.cs

@@ -14,7 +14,6 @@ internal sealed class RequestPortOptions;
 
 internal sealed class RequestInfoExecutor : Executor
 {
-    private const string WrappedRequestsStateKey = nameof(WrappedRequestsStateKey);
     private readonly Dictionary<string, ExternalRequest> _wrappedRequests = [];
     private RequestPort Port { get; }
     private IExternalRequestSink? RequestSink { get; set; }
@@ -125,46 +124,22 @@ internal sealed class RequestInfoExecutor : Executor
             return null;
         }
 
+        if (this._allowWrapped && this._wrappedRequests.TryGetValue(message.RequestId, out ExternalRequest? originalRequest))
+        {
+            await context.SendMessageAsync(originalRequest.RewrapResponse(message), cancellationToken: cancellationToken).ConfigureAwait(false);
+        }
+        else
+        {
+            await context.SendMessageAsync(message, cancellationToken: cancellationToken).ConfigureAwait(false);
+        }
+
         if (!message.Data.IsType(this.Port.Response, out object? data))
         {
             throw this.Port.CreateExceptionForType(message);
         }
 
-        if (this._allowWrapped && this._wrappedRequests.TryGetValue(message.RequestId, out ExternalRequest? originalRequest))
-        {
-            await context.SendMessageAsync(originalRequest.RewrapResponse(message), cancellationToken: cancellationToken).ConfigureAwait(false);
-            this._wrappedRequests.Remove(message.RequestId);
-        }
-        else
-        {
-            await context.SendMessageAsync(message, cancellationToken: cancellationToken).ConfigureAwait(false);
-            await context.SendMessageAsync(data, cancellationToken: cancellationToken).ConfigureAwait(false);
-        }
+        await context.SendMessageAsync(data, cancellationToken: cancellationToken).ConfigureAwait(false);
 
         return message;
     }
-
-    protected internal override async ValueTask OnCheckpointingAsync(IWorkflowContext context, CancellationToken cancellationToken = default)
-    {
-        await context.QueueStateUpdateAsync(WrappedRequestsStateKey,
-                                            new Dictionary<string, ExternalRequest>(this._wrappedRequests, StringComparer.Ordinal),
-                                            cancellationToken: cancellationToken).ConfigureAwait(false);
-        await base.OnCheckpointingAsync(context, cancellationToken).ConfigureAwait(false);
-    }
-
-    protected internal override async ValueTask OnCheckpointRestoredAsync(IWorkflowContext context, CancellationToken cancellationToken = default)
-    {
-        await base.OnCheckpointRestoredAsync(context, cancellationToken).ConfigureAwait(false);
-
-        this._wrappedRequests.Clear();
-
-        Dictionary<string, ExternalRequest> wrappedRequests =
-            await context.ReadStateAsync<Dictionary<string, ExternalRequest>>(WrappedRequestsStateKey, cancellationToken: cancellationToken)
-                         .ConfigureAwait(false) ?? [];
-
-        foreach (KeyValuePair<string, ExternalRequest> wrappedRequest in wrappedRequests)
-        {
-            this._wrappedRequests[wrappedRequest.Key] = wrappedRequest.Value;
-        }
-    }
 }

dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/WorkflowHostExecutor.cs

@@ -1,7 +1,6 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 using System;
-using System.Collections.Concurrent;
 using System.Collections.Generic;
 using System.Diagnostics;
 using System.Diagnostics.CodeAnalysis;
@@ -24,7 +23,6 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
     private InProcessRunner? _activeRunner;
     private InMemoryCheckpointManager? _checkpointManager;
     private readonly ExecutorOptions _options;
-    private readonly ConcurrentDictionary<string, RequestPortInfo> _pendingResponsePorts = new(StringComparer.Ordinal);
 
     private ISuperStepJoinContext? _joinContext;
     private string? _joinId;
@@ -165,11 +163,6 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
 
     private ExternalResponse? CheckAndUnqualifyResponse([DisallowNull] ExternalResponse response)
     {
-        if (this._pendingResponsePorts.TryRemove(response.RequestId, out RequestPortInfo? originalPort))
-        {
-            return response with { PortInfo = originalPort };
-        }
-
         if (!Throw.IfNull(response).PortInfo.PortId.StartsWith($"{this.Id}.", StringComparison.Ordinal))
         {
             return null;
@@ -200,7 +193,6 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
                     break;
                 case RequestInfoEvent requestInfoEvt:
                     ExternalRequest request = requestInfoEvt.Request;
-                    this._pendingResponsePorts[request.RequestId] = request.PortInfo;
                     resultTask = this._joinContext?.SendMessageAsync(this.Id, this.QualifyRequestPortId(request)).AsTask() ?? Task.CompletedTask;
                     break;
                 case WorkflowErrorEvent errorEvent:
@@ -254,13 +246,9 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
     }
 
     private const string CheckpointManagerStateKey = nameof(CheckpointManager);
-    private const string PendingResponsePortsStateKey = nameof(PendingResponsePortsStateKey);
     protected internal override async ValueTask OnCheckpointingAsync(IWorkflowContext context, CancellationToken cancellationToken = default)
     {
         await context.QueueStateUpdateAsync(CheckpointManagerStateKey, this._checkpointManager, cancellationToken: cancellationToken).ConfigureAwait(false);
-        await context.QueueStateUpdateAsync(PendingResponsePortsStateKey,
-                                            new Dictionary<string, RequestPortInfo>(this._pendingResponsePorts, StringComparer.Ordinal),
-                                            cancellationToken: cancellationToken).ConfigureAwait(false);
 
         await base.OnCheckpointingAsync(context, cancellationToken).ConfigureAwait(false);
     }
@@ -281,15 +269,6 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
             await this.ResetAsync().ConfigureAwait(false);
         }
 
-        this._pendingResponsePorts.Clear();
-        Dictionary<string, RequestPortInfo> pendingResponsePorts =
-            await context.ReadStateAsync<Dictionary<string, RequestPortInfo>>(PendingResponsePortsStateKey, cancellationToken: cancellationToken)
-                         .ConfigureAwait(false) ?? [];
-        foreach (KeyValuePair<string, RequestPortInfo> pendingResponsePort in pendingResponsePorts)
-        {
-            this._pendingResponsePorts[pendingResponsePort.Key] = pendingResponsePort.Value;
-        }
-
         await this.EnsureRunSendMessageAsync(resume: true, cancellationToken: cancellationToken).ConfigureAwait(false);
     }
 
@@ -301,8 +280,6 @@ internal class WorkflowHostExecutor : Executor, IAsyncDisposable
             this._run = null;
         }
 
-        this._pendingResponsePorts.Clear();
-
         if (this._activeRunner != null)
         {
             this._activeRunner.OutgoingEvents.EventRaised -= this.ForwardWorkflowEventAsync;

dotnet/src/Microsoft.Agents.AI.Workflows/WorkflowSession.cs

@@ -19,14 +19,7 @@ namespace Microsoft.Agents.AI.Workflows;
 internal sealed class WorkflowSession : AgentSession
 {
     private readonly Workflow _workflow;
-
-    /// <summary>
-    /// The execution environment for this session. Concrete type is required because
-    /// <see cref="CreateOrResumeRunAsync"/> uses the internal
-    /// <see cref="InProcessExecutionEnvironment.ResumeStreamingInternalAsync"/> API.
-    /// </summary>
-    private readonly InProcessExecutionEnvironment _inProcEnvironment;
-
+    private readonly IWorkflowExecutionEnvironment _executionEnvironment;
     private readonly bool _includeExceptionDetails;
     private readonly bool _includeWorkflowOutputsInResponse;
 
@@ -70,22 +63,17 @@ internal sealed class WorkflowSession : AgentSession
     public WorkflowSession(Workflow workflow, string sessionId, IWorkflowExecutionEnvironment executionEnvironment, bool includeExceptionDetails = false, bool includeWorkflowOutputsInResponse = false)
     {
         this._workflow = Throw.IfNull(workflow);
+        this._executionEnvironment = Throw.IfNull(executionEnvironment);
         this._includeExceptionDetails = includeExceptionDetails;
         this._includeWorkflowOutputsInResponse = includeWorkflowOutputsInResponse;
 
-        IWorkflowExecutionEnvironment env = Throw.IfNull(executionEnvironment);
-        if (VerifyCheckpointingConfiguration(env, out InProcessExecutionEnvironment? inProcEnv))
+        if (VerifyCheckpointingConfiguration(executionEnvironment, out InProcessExecutionEnvironment? inProcEnv))
         {
             // We have an InProcessExecutionEnvironment which is not configured for checkpointing. Ensure it has an externalizable checkpoint manager,
             // since we are responsible for maintaining the state.
-            env = inProcEnv.WithCheckpointing(this.EnsureExternalizedInMemoryCheckpointing());
+            this._executionEnvironment = inProcEnv.WithCheckpointing(this.EnsureExternalizedInMemoryCheckpointing());
         }
 
-        this._inProcEnvironment = env as InProcessExecutionEnvironment
-            ?? throw new InvalidOperationException(
-                $"WorkflowSession requires an {nameof(InProcessExecutionEnvironment)}, " +
-                $"but received {env.GetType().Name}.");
-
         this.SessionId = Throw.IfNullOrEmpty(sessionId);
         this.ChatHistoryProvider = new WorkflowChatHistoryProvider();
     }
@@ -98,30 +86,24 @@ internal sealed class WorkflowSession : AgentSession
     public WorkflowSession(Workflow workflow, JsonElement serializedSession, IWorkflowExecutionEnvironment executionEnvironment, bool includeExceptionDetails = false, bool includeWorkflowOutputsInResponse = false, JsonSerializerOptions? jsonSerializerOptions = null)
     {
         this._workflow = Throw.IfNull(workflow);
+        this._executionEnvironment = Throw.IfNull(executionEnvironment);
         this._includeExceptionDetails = includeExceptionDetails;
         this._includeWorkflowOutputsInResponse = includeWorkflowOutputsInResponse;
 
-        IWorkflowExecutionEnvironment env = Throw.IfNull(executionEnvironment);
-
         JsonMarshaller marshaller = new(jsonSerializerOptions);
         SessionState sessionState = marshaller.Marshal<SessionState>(serializedSession);
 
         this._inMemoryCheckpointManager = sessionState.CheckpointManager;
         if (this._inMemoryCheckpointManager != null &&
-            VerifyCheckpointingConfiguration(env, out InProcessExecutionEnvironment? inProcEnv))
+            VerifyCheckpointingConfiguration(executionEnvironment, out InProcessExecutionEnvironment? inProcEnv))
         {
-            env = inProcEnv.WithCheckpointing(this.EnsureExternalizedInMemoryCheckpointing());
+            this._executionEnvironment = inProcEnv.WithCheckpointing(this.EnsureExternalizedInMemoryCheckpointing());
         }
         else if (this._inMemoryCheckpointManager != null)
         {
             throw new ArgumentException("The session was saved with an externalized checkpoint manager, but the incoming execution environment does not support it.", nameof(executionEnvironment));
         }
 
-        this._inProcEnvironment = env as InProcessExecutionEnvironment
-            ?? throw new InvalidOperationException(
-                $"WorkflowSession requires an {nameof(InProcessExecutionEnvironment)}, " +
-                $"but received {env.GetType().Name}.");
-
         this.SessionId = sessionState.SessionId;
         this.ChatHistoryProvider = new WorkflowChatHistoryProvider();
 
@@ -178,15 +160,10 @@ internal sealed class WorkflowSession : AgentSession
         // and does not need to be checked again here.
         if (this.LastCheckpoint is not null)
         {
-            // Use the internal resume path that suppresses pending request republishing.
-            // WorkflowSession handles pending requests itself by converting matching responses
-            // via SendMessagesWithResponseConversionAsync, so event-stream republishing would
-            // cause unwanted duplicate events visible to the consumer.
             StreamingRun run =
-                await this._inProcEnvironment
-                            .ResumeStreamingInternalAsync(this._workflow,
+                await this._executionEnvironment
+                            .ResumeStreamingAsync(this._workflow,
                                                this.LastCheckpoint,
-                                               republishPendingEvents: false,
                                                cancellationToken)
                             .ConfigureAwait(false);
 
@@ -195,7 +172,7 @@ internal sealed class WorkflowSession : AgentSession
             return new ResumeRunResult(run, dispatchInfo);
         }
 
-        StreamingRun newRun = await this._inProcEnvironment
+        StreamingRun newRun = await this._executionEnvironment
                             .RunStreamingAsync(this._workflow,
                                          messages,
                                          this.SessionId,

dotnet/tests/Microsoft.Agents.AI.Workflows.Declarative.IntegrationTests/Framework/WorkflowHarness.cs

@@ -126,13 +126,6 @@ internal sealed class WorkflowHarness(Workflow workflow, string runId)
                     {
                         hasRequest = true;
                     }
-                    else
-                    {
-                        // This is a republished event for the request we're already responding to
-                        // (emitted by RepublishUnservicedRequestsAsync during checkpoint resume).
-                        // Skip yielding it so downstream code doesn't treat it as a new pending request.
-                        continue;
-                    }
                     break;
 
                 case ConversationUpdateEvent conversationEvent:

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

@@ -1,445 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Threading;
-using System.Threading.Tasks;
-using FluentAssertions;
-using Microsoft.Agents.AI.Workflows.InProc;
-using Microsoft.Agents.AI.Workflows.Sample;
-
-namespace Microsoft.Agents.AI.Workflows.UnitTests;
-
-/// <summary>
-/// Regression tests for GH-2485: pending <see cref="RequestInfoEvent"/> objects must be
-/// re-emitted after resuming a workflow from a checkpoint.
-/// </summary>
-public class CheckpointResumeTests
-{
-    /// <summary>
-    /// Verifies that a resumed workflow re-emits <see cref="RequestInfoEvent"/>s for
-    /// pending external requests that existed at the time of the checkpoint.
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Resume_WithPendingRequests_RepublishesRequestInfoEventsAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        RequestPort<string, string> requestPort = RequestPort.Create<string, string>("TestPort");
-        ForwardMessageExecutor<string> processor = new("Processor");
-
-        Workflow workflow = new WorkflowBuilder(requestPort)
-            .AddEdge(requestPort, processor)
-            .Build();
-
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        // Act 1: Run workflow, collect pending requests and a checkpoint.
-        List<ExternalRequest> originalRequests = [];
-        CheckpointInfo? checkpoint = null;
-
-        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
-                                                      .RunStreamingAsync(workflow, "Hello"))
-        {
-            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false))
-            {
-                if (evt is RequestInfoEvent requestInfo)
-                {
-                    originalRequests.Add(requestInfo.Request);
-                }
-
-                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
-                {
-                    checkpoint = cp;
-                }
-            }
-
-            originalRequests.Should().NotBeEmpty("the workflow should have created at least one external request");
-            checkpoint.Should().NotBeNull("a checkpoint should have been created");
-        }
-
-        // Act 2: Resume from the checkpoint.
-        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
-                                                    .ResumeStreamingAsync(workflow, checkpoint!);
-
-        // Assert: The pending requests should be re-emitted.
-        List<ExternalRequest> reEmittedRequests = [];
-        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
-
-        await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
-        {
-            if (evt is RequestInfoEvent requestInfo)
-            {
-                reEmittedRequests.Add(requestInfo.Request);
-            }
-        }
-
-        reEmittedRequests.Should().HaveCount(originalRequests.Count,
-            "all pending requests from the checkpoint should be re-emitted after resume");
-        reEmittedRequests.Select(r => r.RequestId)
-                         .Should().BeEquivalentTo(originalRequests.Select(r => r.RequestId),
-            "the re-emitted request IDs should match the original pending request IDs");
-    }
-
-    /// <summary>
-    /// Verifies that <see cref="RunStatus"/> transitions to <see cref="RunStatus.PendingRequests"/>
-    /// after resuming from a checkpoint with pending external requests (not stuck at NotStarted).
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Resume_WithPendingRequests_RunStatusIsPendingRequestsAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        RequestPort<string, string> requestPort = RequestPort.Create<string, string>("TestPort");
-        ForwardMessageExecutor<string> processor = new("Processor");
-
-        Workflow workflow = new WorkflowBuilder(requestPort)
-            .AddEdge(requestPort, processor)
-            .Build();
-
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        // First run: collect a checkpoint with pending requests.
-        CheckpointInfo? checkpoint = null;
-
-        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
-                                                      .RunStreamingAsync(workflow, "Hello"))
-        {
-            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false))
-            {
-                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
-                {
-                    checkpoint = cp;
-                }
-            }
-
-            checkpoint.Should().NotBeNull();
-        }
-
-        // Act: Resume from the checkpoint and consume events so the run loop processes.
-        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
-                                                    .ResumeStreamingAsync(workflow, checkpoint!);
-
-        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
-        await foreach (WorkflowEvent _ in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
-        {
-            // Consume all events until the stream completes.
-        }
-
-        // Assert
-        RunStatus status = await resumed.GetStatusAsync();
-        status.Should().Be(RunStatus.PendingRequests,
-            "the resumed workflow should report PendingRequests after rehydration");
-    }
-
-    /// <summary>
-    /// Verifies the full roundtrip: resume from checkpoint, observe the re-emitted request,
-    /// send a response, and verify the workflow completes without duplicating the request.
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Resume_RespondToPendingRequest_CompletesWithoutDuplicateAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        RequestPort<string, string> requestPort = RequestPort.Create<string, string>("TestPort");
-        ForwardMessageExecutor<string> processor = new("Processor");
-
-        Workflow workflow = new WorkflowBuilder(requestPort)
-            .AddEdge(requestPort, processor)
-            .Build();
-
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        // First run: collect checkpoint + pending request.
-        ExternalRequest? pendingRequest = null;
-        CheckpointInfo? checkpoint = null;
-
-        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
-                                                      .RunStreamingAsync(workflow, "Hello"))
-        {
-            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false))
-            {
-                if (evt is RequestInfoEvent requestInfo)
-                {
-                    pendingRequest = requestInfo.Request;
-                }
-
-                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
-                {
-                    checkpoint = cp;
-                }
-            }
-
-            pendingRequest.Should().NotBeNull();
-            checkpoint.Should().NotBeNull();
-        }
-
-        // Act: Resume and respond to the restored request.
-        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
-                                                    .ResumeStreamingAsync(workflow, checkpoint!);
-
-        int requestEventCount = 0;
-
-        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
-
-        // Use blockOnPendingRequest: false for the first pass to see the re-emitted requests.
-        await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
-        {
-            if (evt is RequestInfoEvent requestInfo)
-            {
-                requestEventCount++;
-                requestInfo.Request.RequestId.Should().Be(pendingRequest!.RequestId,
-                    "the re-emitted request should match the original");
-            }
-        }
-
-        requestEventCount.Should().Be(1,
-            "the pending request should be emitted exactly once (no duplicates)");
-
-        // Assert intermediate state before responding: the run should be in PendingRequests
-        // and we should have observed the re-emitted request. If the first WatchStreamAsync
-        // didn't complete or yielded nothing, these assertions catch it with a clear message.
-        RunStatus statusBeforeResponse = await resumed.GetStatusAsync();
-        statusBeforeResponse.Should().Be(RunStatus.PendingRequests,
-            "the run should be in PendingRequests state before we send a response");
-
-        // Now send the response and verify the workflow processes it.
-        ExternalResponse response = pendingRequest!.CreateResponse("World");
-        await resumed.SendResponseAsync(response);
-
-        // Consume the resulting events to verify the workflow progresses without errors.
-        List<WorkflowEvent> postResponseEvents = [];
-
-        using CancellationTokenSource cts2 = new(TimeSpan.FromSeconds(10));
-        await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts2.Token))
-        {
-            postResponseEvents.Add(evt);
-        }
-
-        postResponseEvents.Should().NotBeEmpty(
-            "the workflow should process the response and produce events");
-        postResponseEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
-            "no errors should occur when processing the restored request's response");
-    }
-
-    /// <summary>
-    /// Verifies that restoring a live run to a checkpoint re-emits pending requests and allows
-    /// the workflow to continue from that restored point.
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Restore_WithPendingRequests_RepublishesRequestInfoEventsAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        Workflow workflow = CreateSimpleRequestWorkflow();
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        await using StreamingRun run = await env.WithCheckpointing(checkpointManager)
-                                                .RunStreamingAsync(workflow, "Hello");
-
-        (ExternalRequest pendingRequest, CheckpointInfo checkpoint) = await CapturePendingRequestAndCheckpointAsync(run);
-
-        // Advance the run past the checkpoint so the restore has meaningful work to undo.
-        await run.SendResponseAsync(pendingRequest.CreateResponse("World"));
-
-        List<WorkflowEvent> firstCompletionEvents = await ReadToHaltAsync(run);
-        firstCompletionEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
-            "the workflow should continue cleanly before we restore");
-        RunStatus statusAfterFirstResponse = await run.GetStatusAsync();
-        statusAfterFirstResponse.Should().Be(RunStatus.Idle,
-            "the workflow should finish processing the first response before we restore");
-
-        // Act
-        await run.RestoreCheckpointAsync(checkpoint);
-
-        // Assert
-        List<WorkflowEvent> restoredEvents = await ReadToHaltAsync(run);
-        ExternalRequest[] replayedRequests = [.. restoredEvents.OfType<RequestInfoEvent>().Select(evt => evt.Request)];
-
-        replayedRequests.Should().ContainSingle("runtime restore should re-emit the restored pending request");
-        replayedRequests[0].RequestId.Should().Be(pendingRequest.RequestId,
-            "the replayed request should match the request captured at the checkpoint");
-
-        await run.SendResponseAsync(replayedRequests[0].CreateResponse("Again"));
-
-        List<WorkflowEvent> secondCompletionEvents = await ReadToHaltAsync(run);
-        secondCompletionEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
-            "runtime restore replay should not introduce workflow errors");
-        RunStatus statusAfterRestoreResponse = await run.GetStatusAsync();
-        statusAfterRestoreResponse.Should().Be(RunStatus.Idle,
-            "the workflow should be able to continue after the runtime restore replay");
-    }
-
-    /// <summary>
-    /// Verifies that a resumed parent workflow re-emits pending requests that originated in a subworkflow.
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Resume_SubworkflowWithPendingRequests_RepublishesQualifiedRequestInfoEventsAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        Workflow workflow = CreateCheckpointedSubworkflowRequestWorkflow();
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        ExternalRequest pendingRequest;
-        CheckpointInfo checkpoint;
-
-        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
-                                                      .RunStreamingAsync(workflow, "Hello"))
-        {
-            (pendingRequest, checkpoint) = await CapturePendingRequestAndCheckpointAsync(firstRun);
-        }
-
-        // Act
-        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
-                                                    .ResumeStreamingAsync(workflow, checkpoint);
-
-        // Assert
-        List<WorkflowEvent> resumedEvents = await ReadToHaltAsync(resumed);
-        ExternalRequest[] replayedRequests = [.. resumedEvents.OfType<RequestInfoEvent>().Select(evt => evt.Request)];
-
-        replayedRequests.Should().ContainSingle("the resumed parent workflow should surface the subworkflow request once");
-        replayedRequests[0].RequestId.Should().Be(pendingRequest.RequestId,
-            "the replayed subworkflow request should match the checkpointed request");
-        replayedRequests[0].PortInfo.PortId.Should().Be(pendingRequest.PortInfo.PortId,
-            "the replayed request should remain qualified through the subworkflow boundary");
-
-        await resumed.SendResponseAsync(replayedRequests[0].CreateResponse("World"));
-
-        List<WorkflowEvent> completionEvents = await ReadToHaltAsync(resumed);
-        completionEvents.OfType<RequestInfoEvent>().Should().BeEmpty(
-            "the resumed subworkflow request should not be replayed twice");
-        completionEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
-            "subworkflow replay should not introduce workflow errors");
-        RunStatus statusAfterSubworkflowResponse = await resumed.GetStatusAsync();
-        statusAfterSubworkflowResponse.Should().Be(RunStatus.Idle,
-            "the resumed subworkflow should continue after responding to the replayed request");
-    }
-
-    /// <summary>
-    /// Verifies that when <c>republishPendingEvents</c> is <see langword="false"/>,
-    /// no <see cref="RequestInfoEvent"/> is re-emitted after resuming from a checkpoint.
-    /// </summary>
-    [Theory]
-    [InlineData(ExecutionEnvironment.InProcess_OffThread)]
-    [InlineData(ExecutionEnvironment.InProcess_Lockstep)]
-    internal async Task Checkpoint_Resume_WithRepublishDisabled_DoesNotEmitRequestInfoEventsAsync(ExecutionEnvironment environment)
-    {
-        // Arrange
-        RequestPort<string, string> requestPort = RequestPort.Create<string, string>("TestPort");
-        ForwardMessageExecutor<string> processor = new("Processor");
-
-        Workflow workflow = new WorkflowBuilder(requestPort)
-            .AddEdge(requestPort, processor)
-            .Build();
-
-        CheckpointManager checkpointManager = CheckpointManager.CreateInMemory();
-        InProcessExecutionEnvironment env = environment.ToWorkflowExecutionEnvironment();
-
-        // First run: collect a checkpoint with pending requests.
-        CheckpointInfo? checkpoint = null;
-
-        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
-                                                      .RunStreamingAsync(workflow, "Hello"))
-        {
-            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false))
-            {
-                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
-                {
-                    checkpoint = cp;
-                }
-            }
-
-            checkpoint.Should().NotBeNull();
-        }
-
-        // Act: Resume with republishPendingEvents: false via the internal API.
-        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
-                                                    .ResumeStreamingInternalAsync(workflow, checkpoint!, republishPendingEvents: false);
-
-        // Assert: No RequestInfoEvent should appear in the event stream.
-        int requestEventCount = 0;
-        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
-        await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
-        {
-            if (evt is RequestInfoEvent)
-            {
-                requestEventCount++;
-            }
-        }
-
-        requestEventCount.Should().Be(0,
-            "no RequestInfoEvent should be emitted when republishPendingEvents is false");
-    }
-
-    private static Workflow CreateSimpleRequestWorkflow(
-        string requestPortId = "TestPort",
-        string processorId = "Processor")
-    {
-        RequestPort<string, string> requestPort = RequestPort.Create<string, string>(requestPortId);
-        ForwardMessageExecutor<string> processor = new(processorId);
-
-        return new WorkflowBuilder(requestPort)
-            .AddEdge(requestPort, processor)
-            .Build();
-    }
-
-    private static Workflow CreateCheckpointedSubworkflowRequestWorkflow()
-    {
-        ExecutorBinding subworkflow = CreateSimpleRequestWorkflow(
-                requestPortId: "InnerTestPort",
-                processorId: "InnerProcessor")
-            .BindAsExecutor("Subworkflow");
-
-        return new WorkflowBuilder(subworkflow)
-            .AddExternalRequest<string, string>(subworkflow, id: "ForwardedSubworkflowRequest")
-            .Build();
-    }
-
-    private static async ValueTask<(ExternalRequest PendingRequest, CheckpointInfo Checkpoint)> CapturePendingRequestAndCheckpointAsync(StreamingRun run)
-    {
-        ExternalRequest? pendingRequest = null;
-        CheckpointInfo? checkpoint = null;
-
-        await foreach (WorkflowEvent evt in run.WatchStreamAsync(blockOnPendingRequest: false))
-        {
-            if (evt is RequestInfoEvent requestInfo)
-            {
-                pendingRequest ??= requestInfo.Request;
-            }
-
-            if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
-            {
-                checkpoint = cp;
-            }
-        }
-
-        pendingRequest.Should().NotBeNull("the workflow should have emitted a pending request");
-        checkpoint.Should().NotBeNull("the workflow should have produced a checkpoint");
-        return (pendingRequest!, checkpoint!);
-    }
-
-    private static async ValueTask<List<WorkflowEvent>> ReadToHaltAsync(StreamingRun run)
-    {
-        List<WorkflowEvent> events = [];
-        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
-
-        await foreach (WorkflowEvent evt in run.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
-        {
-            events.Add(evt);
-        }
-
-        return events;
-    }
-}

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

@@ -132,53 +132,6 @@ public class InProcessExecutionTests
             "both versions should produce the same number of agent events");
     }
 
-    /// <summary>
-    /// This test checks that the logic around waiting for input and halting appropriately works right when the
-    /// workflow runs to halting before the EventStream is watched by the user.
-    /// </summary>
-    [Fact]
-    public async Task RunStreamingAsyncWaitToTakeStreamAsync()
-    {
-        // Arrange: Create a simple agent that responds to messages
-        var agent = new SimpleTestAgent("test-agent");
-        var workflow = AgentWorkflowBuilder.BuildSequential(agent);
-        var inputMessage = new ChatMessage(ChatRole.User, "Hello");
-
-        // Act: Execute using streaming version with TurnToken
-        await using StreamingRun run = await InProcessExecution.RunStreamingAsync(workflow, new List<ChatMessage> { inputMessage });
-
-        // Send TurnToken to actually trigger execution (this is the key step)
-        bool messageSent = await run.TrySendMessageAsync(new TurnToken(emitEvents: true));
-        messageSent.Should().BeTrue("TurnToken should be accepted");
-
-        while (await run.GetStatusAsync() != RunStatus.Idle)
-        {
-            await Task.Delay(200);
-        }
-
-        // Collect events
-        List<WorkflowEvent> events = [];
-
-        await foreach (WorkflowEvent evt in run.WatchStreamAsync())
-        {
-            events.Add(evt);
-        }
-
-        // Assert: The workflow should have executed and produced events
-        RunStatus status = await run.GetStatusAsync();
-        status.Should().Be(RunStatus.Idle, "workflow should complete execution");
-
-        events.Should().NotBeEmpty("workflow should produce events during execution");
-
-        // Check that we have agent execution events
-        var agentEvents = events.OfType<AgentResponseUpdateEvent>().ToList();
-        agentEvents.Should().NotBeEmpty("agent should have executed and produced update events");
-
-        // Check that we have output events
-        var outputEvents = events.OfType<WorkflowOutputEvent>().ToList();
-        outputEvents.Should().NotBeEmpty("workflow should produce output events");
-    }
-
     /// <summary>
     /// Simple test agent that echoes back the input message.
     /// </summary>

python/packages/a2a/agent_framework_a2a/_agent.py

@@ -35,9 +35,9 @@ from agent_framework import (
     AgentResponseUpdate,
     AgentSession,
     BaseAgent,
+    BaseHistoryProvider,
     Content,
     ContinuationToken,
-    HistoryProvider,
     Message,
     ResponseStream,
     SessionContext,
@@ -353,7 +353,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
 
         # Run before_run providers (forward order)
         for provider in self.context_providers:
-            if isinstance(provider, HistoryProvider) and not provider.load_messages:
+            if isinstance(provider, BaseHistoryProvider) and not provider.load_messages:
                 continue
             if session is None:
                 raise RuntimeError("Provider session must be available when context providers are configured.")

python/packages/a2a/tests/test_a2a_agent.py

@@ -24,8 +24,8 @@ from agent_framework import (
     AgentResponse,
     AgentResponseUpdate,
     AgentSession,
+    BaseContextProvider,
     Content,
-    ContextProvider,
     Message,
     SessionContext,
 )
@@ -869,7 +869,7 @@ async def test_poll_task_completed(a2a_agent: A2AAgent, mock_a2a_client: MockA2A
 # region Context Provider Tests
 
 
-class TrackingContextProvider(ContextProvider):
+class TrackingContextProvider(BaseContextProvider):
     """A context provider that records when before_run and after_run are called."""
 
     def __init__(self) -> None:

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

@@ -1,9 +1,9 @@
 # Copyright (c) Microsoft. All rights reserved.
 
-"""New-pattern Azure AI Search context provider using ContextProvider.
+"""New-pattern Azure AI Search context provider using BaseContextProvider.
 
 This module provides ``AzureAISearchContextProvider``, built on the new
-:class:`ContextProvider` hooks pattern.
+:class:`BaseContextProvider` hooks pattern.
 """
 
 from __future__ import annotations
@@ -11,21 +11,11 @@ from __future__ import annotations
 import logging
 import sys
 from collections.abc import Awaitable, Callable
-from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypedDict, overload
+from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypedDict
 
-from agent_framework import (
-    AGENT_FRAMEWORK_USER_AGENT,
-    AgentSession,
-    Annotation,
-    Content,
-    ContextProvider,
-    Message,
-    SecretString,
-    SessionContext,
-    SupportsGetEmbeddings,
-    load_settings,
-)
-from agent_framework.exceptions import SettingNotFoundError
+from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Annotation, Content, Message, SupportsGetEmbeddings
+from agent_framework._sessions import AgentSession, BaseContextProvider, SessionContext
+from agent_framework._settings import SecretString, load_settings
 from azure.core.credentials import AzureKeyCredential, TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
 from azure.core.exceptions import ResourceNotFoundError
@@ -121,9 +111,6 @@ except ImportError:
     _agentic_retrieval_available = False
 
 AzureCredentialTypes = TokenCredential | AsyncTokenCredential
-EmbeddingFunction = Callable[[str], Awaitable[list[float]]] | SupportsGetEmbeddings[str, list[float], Any]
-KnowledgeBaseOutputModeLiteral = Literal["extractive_data", "answer_synthesis"]
-RetrievalReasoningEffortLiteral = Literal["minimal", "medium", "low"]
 
 logger = logging.getLogger("agent_framework.azure_ai_search")
 
@@ -154,8 +141,8 @@ class AzureAISearchSettings(TypedDict, total=False):
     api_key: SecretString | None
 
 
-class AzureAISearchContextProvider(ContextProvider):
-    """Azure AI Search context provider using the new ContextProvider hooks pattern.
+class AzureAISearchContextProvider(BaseContextProvider):
+    """Azure AI Search context provider using the new BaseContextProvider hooks pattern.
 
     Retrieves relevant context from Azure AI Search using semantic or agentic search
     modes.
@@ -164,230 +151,6 @@ class AzureAISearchContextProvider(ContextProvider):
     _DEFAULT_SEARCH_CONTEXT_PROMPT: ClassVar[str] = "Use the following context to answer the question:"
     DEFAULT_SOURCE_ID: ClassVar[str] = "azure_ai_search"
 
-    @overload
-    def __init__(
-        self,
-        source_id: str = DEFAULT_SOURCE_ID,
-        endpoint: str | None = None,
-        index_name: str | None = None,
-        api_key: str | AzureKeyCredential | None = None,
-        credential: AzureCredentialTypes | None = None,
-        *,
-        mode: Literal["semantic"] = "semantic",
-        top_k: int = 5,
-        semantic_configuration_name: str | None = None,
-        vector_field_name: str | None = None,
-        embedding_function: EmbeddingFunction | None = None,
-        context_prompt: str | None = None,
-        azure_openai_resource_url: str | None = None,
-        model_deployment_name: str | None = None,
-        model_name: str | None = None,
-        knowledge_base_name: None = None,
-        retrieval_instructions: str | None = None,
-        azure_openai_api_key: str | None = None,
-        knowledge_base_output_mode: KnowledgeBaseOutputModeLiteral = "extractive_data",
-        retrieval_reasoning_effort: RetrievalReasoningEffortLiteral = "minimal",
-        agentic_message_history_count: int = _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize a semantic Azure AI Search context provider.
-
-        Keyword Args:
-            source_id: Unique identifier for this provider instance.
-            endpoint: Azure AI Search endpoint URL.
-            index_name: Name of the search index to query.
-            api_key: API key for authentication.
-            credential: Azure credential for managed identity authentication.
-            mode: Must be ``"semantic"`` for this overload.
-            top_k: Maximum number of documents to retrieve.
-            semantic_configuration_name: Name of the semantic configuration in the index.
-            vector_field_name: Name of the vector field in the index.
-            embedding_function: Embedding provider used for vector search.
-            context_prompt: Custom prompt to prepend to retrieved context.
-            azure_openai_resource_url: Unused in semantic mode.
-            model_deployment_name: Unused in semantic mode.
-            model_name: Unused in semantic mode.
-            knowledge_base_name: Must be ``None`` for this overload.
-            retrieval_instructions: Unused in semantic mode.
-            azure_openai_api_key: Unused in semantic mode.
-            knowledge_base_output_mode: Unused in semantic mode.
-            retrieval_reasoning_effort: Unused in semantic mode.
-            agentic_message_history_count: Unused in semantic mode.
-            env_file_path: Optional ``.env`` file checked before process environment variables.
-            env_file_encoding: Encoding for the ``.env`` file.
-        """
-        ...
-
-    @overload
-    def __init__(
-        self,
-        source_id: str = DEFAULT_SOURCE_ID,
-        endpoint: str | None = None,
-        index_name: str | None = None,
-        api_key: str | AzureKeyCredential | None = None,
-        credential: AzureCredentialTypes | None = None,
-        *,
-        mode: Literal["agentic"],
-        top_k: int = 5,
-        semantic_configuration_name: str | None = None,
-        vector_field_name: str | None = None,
-        embedding_function: EmbeddingFunction | None = None,
-        context_prompt: str | None = None,
-        azure_openai_resource_url: str,
-        model_deployment_name: str,
-        model_name: str | None = None,
-        knowledge_base_name: None = None,
-        retrieval_instructions: str | None = None,
-        azure_openai_api_key: str | None = None,
-        knowledge_base_output_mode: KnowledgeBaseOutputModeLiteral = "extractive_data",
-        retrieval_reasoning_effort: RetrievalReasoningEffortLiteral = "minimal",
-        agentic_message_history_count: int = _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize an agentic provider that creates a Knowledge Base from an index.
-
-        Keyword Args:
-            source_id: Unique identifier for this provider instance.
-            endpoint: Azure AI Search endpoint URL.
-            index_name: Name of the search index used to create the Knowledge Base.
-            api_key: API key for authentication.
-            credential: Azure credential for managed identity authentication.
-            mode: Must be ``"agentic"`` for this overload.
-            top_k: Maximum number of documents to retrieve.
-            semantic_configuration_name: Semantic configuration name used by hybrid search operations.
-            vector_field_name: Vector field name used by hybrid search operations.
-            embedding_function: Embedding provider used for vector search.
-            context_prompt: Custom prompt to prepend to retrieved context.
-            azure_openai_resource_url: Azure OpenAI resource URL for Knowledge Base creation.
-            model_deployment_name: Azure OpenAI deployment used by the generated Knowledge Base.
-            model_name: Underlying model name for the Knowledge Base model configuration.
-            knowledge_base_name: Must be ``None`` for this overload.
-            retrieval_instructions: Custom instructions for Knowledge Base retrieval.
-            azure_openai_api_key: Optional Azure OpenAI API key for Knowledge Base creation.
-            knowledge_base_output_mode: Output mode for Knowledge Base retrieval.
-            retrieval_reasoning_effort: Reasoning effort for query planning.
-            agentic_message_history_count: Number of recent messages included in retrieval.
-            env_file_path: Optional ``.env`` file checked before process environment variables.
-            env_file_encoding: Encoding for the ``.env`` file.
-        """
-        ...
-
-    @overload
-    def __init__(
-        self,
-        source_id: str = DEFAULT_SOURCE_ID,
-        endpoint: str | None = None,
-        index_name: None = None,
-        api_key: str | AzureKeyCredential | None = None,
-        credential: AzureCredentialTypes | None = None,
-        *,
-        mode: Literal["agentic"],
-        top_k: int = 5,
-        semantic_configuration_name: str | None = None,
-        vector_field_name: str | None = None,
-        embedding_function: EmbeddingFunction | None = None,
-        context_prompt: str | None = None,
-        azure_openai_resource_url: str | None = None,
-        model_deployment_name: str | None = None,
-        model_name: str | None = None,
-        knowledge_base_name: str,
-        retrieval_instructions: str | None = None,
-        azure_openai_api_key: str | None = None,
-        knowledge_base_output_mode: KnowledgeBaseOutputModeLiteral = "extractive_data",
-        retrieval_reasoning_effort: RetrievalReasoningEffortLiteral = "minimal",
-        agentic_message_history_count: int = _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize an agentic provider that connects to an existing Knowledge Base.
-
-        Keyword Args:
-            source_id: Unique identifier for this provider instance.
-            endpoint: Azure AI Search endpoint URL.
-            index_name: Must be ``None`` for this overload.
-            knowledge_base_name: Name of the existing Knowledge Base to use.
-            api_key: API key for authentication.
-            credential: Azure credential for managed identity authentication.
-            mode: Must be ``"agentic"`` for this overload.
-            top_k: Maximum number of documents to retrieve.
-            semantic_configuration_name: Semantic configuration name used by hybrid search operations.
-            vector_field_name: Vector field name used by hybrid search operations.
-            embedding_function: Embedding provider used for vector search.
-            context_prompt: Custom prompt to prepend to retrieved context.
-            azure_openai_resource_url: Unused when connecting to an existing Knowledge Base.
-            model_deployment_name: Unused when connecting to an existing Knowledge Base.
-            model_name: Unused when connecting to an existing Knowledge Base.
-            retrieval_instructions: Custom instructions for Knowledge Base retrieval.
-            azure_openai_api_key: Unused when connecting to an existing Knowledge Base.
-            knowledge_base_output_mode: Output mode for Knowledge Base retrieval.
-            retrieval_reasoning_effort: Reasoning effort for query planning.
-            agentic_message_history_count: Number of recent messages included in retrieval.
-            env_file_path: Optional ``.env`` file checked before process environment variables.
-            env_file_encoding: Encoding for the ``.env`` file.
-        """
-        ...
-
-    @overload
-    def __init__(
-        self,
-        source_id: str = DEFAULT_SOURCE_ID,
-        endpoint: str | None = None,
-        index_name: None = None,
-        api_key: str | AzureKeyCredential | None = None,
-        credential: AzureCredentialTypes | None = None,
-        *,
-        mode: Literal["agentic"],
-        top_k: int = 5,
-        semantic_configuration_name: str | None = None,
-        vector_field_name: str | None = None,
-        embedding_function: EmbeddingFunction | None = None,
-        context_prompt: str | None = None,
-        azure_openai_resource_url: str | None = None,
-        model_deployment_name: str | None = None,
-        model_name: str | None = None,
-        knowledge_base_name: None = None,
-        retrieval_instructions: str | None = None,
-        azure_openai_api_key: str | None = None,
-        knowledge_base_output_mode: KnowledgeBaseOutputModeLiteral = "extractive_data",
-        retrieval_reasoning_effort: RetrievalReasoningEffortLiteral = "minimal",
-        agentic_message_history_count: int = _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize an agentic provider using environment-resolved setup.
-
-        This overload is for agentic initialization where ``index_name`` or
-        ``knowledge_base_name`` is supplied by ``env_file_path`` or the
-        ``AZURE_SEARCH_*`` environment variables.
-
-        Keyword Args:
-            source_id: Unique identifier for this provider instance.
-            endpoint: Azure AI Search endpoint URL.
-            index_name: Resolved from ``env_file_path`` or ``AZURE_SEARCH_INDEX_NAME``.
-            api_key: API key for authentication.
-            credential: Azure credential for managed identity authentication.
-            mode: Must be ``"agentic"`` for this overload.
-            top_k: Maximum number of documents to retrieve.
-            semantic_configuration_name: Semantic configuration name used by hybrid search operations.
-            vector_field_name: Vector field name used by hybrid search operations.
-            embedding_function: Embedding provider used for vector search.
-            context_prompt: Custom prompt to prepend to retrieved context.
-            azure_openai_resource_url: Azure OpenAI resource URL when creating a Knowledge Base from an index.
-            model_deployment_name: Azure OpenAI deployment when creating a Knowledge Base from an index.
-            model_name: Underlying model name for Knowledge Base model configuration.
-            knowledge_base_name: Resolved from ``env_file_path`` or ``AZURE_SEARCH_KNOWLEDGE_BASE_NAME``.
-            retrieval_instructions: Custom instructions for Knowledge Base retrieval.
-            azure_openai_api_key: Optional Azure OpenAI API key for Knowledge Base creation.
-            knowledge_base_output_mode: Output mode for Knowledge Base retrieval.
-            retrieval_reasoning_effort: Reasoning effort for query planning.
-            agentic_message_history_count: Number of recent messages included in retrieval.
-            env_file_path: Optional ``.env`` file checked before process environment variables.
-            env_file_encoding: Encoding for the ``.env`` file.
-        """
-        ...
-
     def __init__(
         self,
         source_id: str = DEFAULT_SOURCE_ID,
@@ -400,7 +163,9 @@ class AzureAISearchContextProvider(ContextProvider):
         top_k: int = 5,
         semantic_configuration_name: str | None = None,
         vector_field_name: str | None = None,
-        embedding_function: EmbeddingFunction | None = None,
+        embedding_function: Callable[[str], Awaitable[list[float]]]
+        | SupportsGetEmbeddings[str, list[float], Any]
+        | None = None,
         context_prompt: str | None = None,
         azure_openai_resource_url: str | None = None,
         model_deployment_name: str | None = None,
@@ -408,8 +173,8 @@ class AzureAISearchContextProvider(ContextProvider):
         knowledge_base_name: str | None = None,
         retrieval_instructions: str | None = None,
         azure_openai_api_key: str | None = None,
-        knowledge_base_output_mode: KnowledgeBaseOutputModeLiteral = "extractive_data",
-        retrieval_reasoning_effort: RetrievalReasoningEffortLiteral = "minimal",
+        knowledge_base_output_mode: Literal["extractive_data", "answer_synthesis"] = "extractive_data",
+        retrieval_reasoning_effort: Literal["minimal", "medium", "low"] = "minimal",
         agentic_message_history_count: int = _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
@@ -419,9 +184,7 @@ class AzureAISearchContextProvider(ContextProvider):
         Args:
             source_id: Unique identifier for this provider instance.
             endpoint: Azure AI Search endpoint URL.
-            index_name: Name of the search index to query. In agentic mode, providing this
-                explicitly selects the index-backed setup and ignores any environment-provided
-                knowledge base name.
+            index_name: Name of the search index to query.
             api_key: API key for authentication.
             credential: Azure credential for managed identity authentication.
                 Accepts a TokenCredential, AsyncTokenCredential, or a callable token provider.
@@ -434,9 +197,7 @@ class AzureAISearchContextProvider(ContextProvider):
             azure_openai_resource_url: Azure OpenAI resource URL for Knowledge Base.
             model_deployment_name: Model deployment name in Azure OpenAI.
             model_name: The underlying model name.
-            knowledge_base_name: Name of an existing Knowledge Base to use. In agentic mode,
-                providing this explicitly selects the Knowledge Base-backed setup and ignores any
-                environment-provided index name.
+            knowledge_base_name: Name of an existing Knowledge Base to use.
             retrieval_instructions: Custom instructions for Knowledge Base retrieval.
             azure_openai_api_key: Azure OpenAI API key.
             knowledge_base_output_mode: Output mode for Knowledge Base retrieval.
@@ -447,26 +208,12 @@ class AzureAISearchContextProvider(ContextProvider):
         """
         super().__init__(source_id)
 
-        required: list[str | tuple[str, ...]]
-        ignored_agentic_field: Literal["index_name", "knowledge_base_name"] | None = None
-        explicit_index_name = index_name is not None
-        explicit_knowledge_base_name = knowledge_base_name is not None
-
+        # Determine which fields are required based on mode
+        required: list[str | tuple[str, ...]] = ["endpoint"]
         if mode == "semantic":
-            required = ["endpoint", "index_name"]
-        elif explicit_index_name and explicit_knowledge_base_name:
-            raise SettingNotFoundError(
-                "Only one of 'index_name', 'knowledge_base_name' may be provided, "
-                "but multiple were set: 'index_name', 'knowledge_base_name'."
-            )
-        elif explicit_index_name:
-            required = ["endpoint", "index_name"]
-            ignored_agentic_field = "knowledge_base_name"
-        elif explicit_knowledge_base_name:
-            required = ["endpoint", "knowledge_base_name"]
-            ignored_agentic_field = "index_name"
-        else:
-            required = ["endpoint", ("index_name", "knowledge_base_name")]
+            required.append("index_name")
+        elif mode == "agentic":
+            required.append(("index_name", "knowledge_base_name"))
 
         # Load settings from environment/file
         settings = load_settings(
@@ -480,8 +227,6 @@ class AzureAISearchContextProvider(ContextProvider):
             env_file_path=env_file_path,
             env_file_encoding=env_file_encoding,
         )
-        if ignored_agentic_field is not None:
-            settings[ignored_agentic_field] = None
 
         if mode == "agentic" and settings.get("index_name") and not model_deployment_name:
             raise ValueError(

python/packages/azure-ai-search/tests/test_aisearch_context_provider.py

@@ -283,37 +283,6 @@ class TestInitAgenticValidation:
         assert provider._use_existing_knowledge_base is False
         assert provider.knowledge_base_name == "idx-kb"
 
-    def test_agentic_explicit_kb_ignores_env_index_name(self) -> None:
-        with patch.dict(os.environ, {"AZURE_SEARCH_INDEX_NAME": "env-index"}, clear=False):
-            provider = AzureAISearchContextProvider(
-                source_id="s",
-                endpoint="https://test.search.windows.net",
-                knowledge_base_name="my-kb",
-                api_key="key",
-                mode="agentic",
-            )
-
-        assert provider.index_name is None
-        assert provider.knowledge_base_name == "my-kb"
-        assert provider._use_existing_knowledge_base is True
-        assert provider._search_client is None
-
-    def test_agentic_explicit_index_ignores_env_kb_name(self) -> None:
-        with patch.dict(os.environ, {"AZURE_SEARCH_KNOWLEDGE_BASE_NAME": "env-kb"}, clear=False):
-            provider = AzureAISearchContextProvider(
-                source_id="s",
-                endpoint="https://test.search.windows.net",
-                index_name="idx",
-                api_key="key",
-                mode="agentic",
-                model_deployment_name="deploy",
-                azure_openai_resource_url="https://aoai.openai.azure.com",
-            )
-
-        assert provider.index_name == "idx"
-        assert provider.knowledge_base_name == "idx-kb"
-        assert provider._use_existing_knowledge_base is False
-
 
 # -- __aenter__ / __aexit__ ---------------------------------------------------
 

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

@@ -11,7 +11,7 @@ from collections.abc import Sequence
 from typing import Any, ClassVar, TypedDict
 
 from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Message
-from agent_framework._sessions import HistoryProvider
+from agent_framework._sessions import BaseHistoryProvider
 from agent_framework._settings import SecretString, load_settings
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential
@@ -32,8 +32,8 @@ class AzureCosmosHistorySettings(TypedDict, total=False):
     key: SecretString | None
 
 
-class CosmosHistoryProvider(HistoryProvider):
-    """Azure Cosmos DB-backed history provider using HistoryProvider hooks."""
+class CosmosHistoryProvider(BaseHistoryProvider):
+    """Azure Cosmos DB-backed history provider using BaseHistoryProvider hooks."""
 
     DEFAULT_SOURCE_ID: ClassVar[str] = "azure_cosmos_history"
     _BATCH_OPERATION_LIMIT: ClassVar[int] = 100

python/packages/claude/agent_framework_claude/_agent.py

@@ -16,8 +16,8 @@ from agent_framework import (
     AgentRunInputs,
     AgentSession,
     BaseAgent,
+    BaseContextProvider,
     Content,
-    ContextProvider,
     FunctionTool,
     Message,
     ResponseStream,
@@ -223,7 +223,7 @@ class RawClaudeAgent(BaseAgent, Generic[OptionsT]):
         id: str | None = None,
         name: str | None = None,
         description: str | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[AgentMiddlewareTypes] | None = None,
         tools: ToolTypes | Callable[..., Any] | str | Sequence[ToolTypes | Callable[..., Any] | str] | None = None,
         default_options: OptionsT | MutableMapping[str, Any] | None = None,

python/packages/copilotstudio/agent_framework_copilotstudio/_agent.py

@@ -11,8 +11,8 @@ from agent_framework import (
     AgentResponseUpdate,
     AgentSession,
     BaseAgent,
+    BaseContextProvider,
     Content,
-    ContextProvider,
     Message,
     ResponseStream,
     normalize_messages,
@@ -60,7 +60,7 @@ class CopilotStudioAgent(BaseAgent):
         id: str | None = None,
         name: str | None = None,
         description: str | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: list[AgentMiddlewareTypes] | None = None,
         environment_id: str | None = None,
         agent_identifier: str | None = None,

python/packages/core/AGENTS.md

@@ -61,8 +61,8 @@ agent_framework/
 
 - **`AgentSession`** - Manages conversation state and session metadata
 - **`SessionContext`** - Context object for session-scoped data during agent runs
-- **`ContextProvider`** - Base class for context providers (RAG, memory systems)
-- **`HistoryProvider`** - Base class for conversation history storage
+- **`BaseContextProvider`** - Base class for context providers (RAG, memory systems)
+- **`BaseHistoryProvider`** - Base class for conversation history storage
 
 ### Skills (`_skills.py`)
 
@@ -70,7 +70,7 @@ agent_framework/
 - **`SkillResource`** - Named supplementary content attached to a skill; holds either static `content` or a dynamic `function` (sync or async). Exactly one must be provided.
 - **`SkillScript`** - An executable script attached to a skill; holds either an inline `function` (code-defined, runs in-process) or a `path` to a file on disk (file-based, delegated to a runner). Exactly one must be provided.
 - **`SkillScriptRunner`** - Protocol for file-based script execution. Any callable matching `(skill, script, args) -> Any` satisfies it. Code-defined scripts do not use a runner.
-- **`SkillsProvider`** - Context provider (extends `ContextProvider`) that discovers file-based skills from `SKILL.md` files and/or accepts code-defined `Skill` instances. Follows progressive disclosure: advertise → load → read resources / run scripts.
+- **`SkillsProvider`** - Context provider (extends `BaseContextProvider`) that discovers file-based skills from `SKILL.md` files and/or accepts code-defined `Skill` instances. Follows progressive disclosure: advertise → load → read resources / run scripts.
 
 ### Workflows (`_workflows/`)
 

python/packages/core/agent_framework/__init__.py

@@ -102,10 +102,8 @@ from ._middleware import (
 )
 from ._sessions import (
     AgentSession,
-    BaseContextProvider,  # type: ignore[reportDeprecated]
-    BaseHistoryProvider,  # type: ignore[reportDeprecated]
-    ContextProvider,
-    HistoryProvider,
+    BaseContextProvider,
+    BaseHistoryProvider,
     InMemoryHistoryProvider,
     SessionContext,
     register_state_type,
@@ -298,7 +296,6 @@ __all__ = [
     "CompactionProvider",
     "CompactionStrategy",
     "Content",
-    "ContextProvider",
     "ContinuationToken",
     "ConversationSplit",
     "ConversationSplitter",
@@ -334,7 +331,6 @@ __all__ = [
     "FunctionTool",
     "GeneratedEmbeddings",
     "GraphConnectivityError",
-    "HistoryProvider",
     "InMemoryCheckpointStorage",
     "InMemoryHistoryProvider",
     "InProcRunnerContext",

python/packages/core/agent_framework/_agents.py

@@ -29,16 +29,14 @@ from . import _tools as _tool_utils  # pyright: ignore[reportPrivateUsage]
 from ._clients import BaseChatClient, SupportsChatGetResponse
 from ._docstrings import apply_layered_docstring
 from ._mcp import LOG_LEVEL_MAPPING, MCPTool
-from ._middleware import AgentMiddlewareLayer, FunctionInvocationContext, MiddlewareTypes, categorize_middleware
+from ._middleware import AgentMiddlewareLayer, FunctionInvocationContext, MiddlewareTypes
 from ._serialization import SerializationMixin
 from ._sessions import (
     AgentSession,
-    ContextProvider,
-    HistoryProvider,
+    BaseContextProvider,
+    BaseHistoryProvider,
     InMemoryHistoryProvider,
-    PerServiceCallHistoryPersistingMiddleware,
     SessionContext,
-    is_local_history_conversation_id,
 )
 from ._tools import FunctionInvocationLayer, FunctionTool, ToolTypes, normalize_tools
 from ._types import (
@@ -52,7 +50,7 @@ from ._types import (
     map_chat_to_agent_update,
     normalize_messages,
 )
-from .exceptions import AgentInvalidRequestException, AgentInvalidResponseException, UserInputRequiredException
+from .exceptions import AgentInvalidResponseException, UserInputRequiredException
 from .observability import AgentTelemetryLayer
 
 if sys.version_info >= (3, 13):
@@ -168,7 +166,6 @@ class _RunContext(TypedDict):
     input_messages: Sequence[Message]
     session_messages: Sequence[Message]
     agent_name: str
-    suppress_response_id: bool
     chat_options: MutableMapping[str, Any]
     compaction_strategy: CompactionStrategy | None
     tokenizer: TokenizerProtocol | None
@@ -369,7 +366,6 @@ class BaseAgent(SerializationMixin):
     """
 
     DEFAULT_EXCLUDE: ClassVar[set[str]] = {"additional_properties"}
-    require_per_service_call_history_persistence: bool = False
 
     def __init__(
         self,
@@ -377,7 +373,7 @@ class BaseAgent(SerializationMixin):
         id: str | None = None,
         name: str | None = None,
         description: str | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
         additional_properties: MutableMapping[str, Any] | None = None,
     ) -> None:
@@ -397,7 +393,7 @@ class BaseAgent(SerializationMixin):
         self.id = id
         self.name = name
         self.description = description
-        self.context_providers: list[ContextProvider] = list(context_providers or [])
+        self.context_providers: list[BaseContextProvider] = list(context_providers or [])
         self.middleware: list[MiddlewareTypes] | None = (
             cast(list[MiddlewareTypes], middleware) if middleware is not None else None
         )
@@ -459,12 +455,7 @@ class BaseAgent(SerializationMixin):
         if provider_session is None and self.context_providers:
             provider_session = AgentSession()
 
-        per_service_call_history_required = self.require_per_service_call_history_persistence and any(
-            isinstance(provider, HistoryProvider) for provider in self.context_providers
-        )
         for provider in reversed(self.context_providers):
-            if per_service_call_history_required and isinstance(provider, HistoryProvider):
-                continue
             if provider_session is None:
                 raise RuntimeError("Provider session must be available when context providers are configured.")
             await provider.after_run(
@@ -665,9 +656,8 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         description: str | None = None,
         tools: ToolTypes | Callable[..., Any] | Sequence[ToolTypes | Callable[..., Any]] | None = None,
         default_options: OptionsCoT | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
         additional_properties: MutableMapping[str, Any] | None = None,
@@ -685,11 +675,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
             description: A brief description of the agent's purpose.
             context_providers: Context providers to include during agent invocation.
             middleware: List of middleware to intercept agent and function invocations.
-            require_per_service_call_history_persistence: When True, history providers are invoked
-                around each model call instead of once per ``run()`` when the service
-                is not already storing history. If service-side storage is active for
-                the run, the agent skips local history providers and relies on the
-                service-managed conversation instead.
             default_options: A TypedDict containing chat options. When using a typed agent like
                 ``Agent[OpenAIChatOptions]``, this enables IDE autocomplete for
                 provider-specific options including temperature, max_tokens, model_id,
@@ -721,7 +706,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         )
         self.client = client
         self.compaction_strategy = compaction_strategy
-        self.require_per_service_call_history_persistence = require_per_service_call_history_persistence
         self.tokenizer = tokenizer
 
         # Get tools from options or named parameter (named param takes precedence)
@@ -780,35 +764,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
                 await self._async_exit_stack.enter_async_context(context_manager)
         return self
 
-    def _get_history_providers(self) -> list[HistoryProvider]:
-        return [provider for provider in self.context_providers if isinstance(provider, HistoryProvider)]
-
-    def _resolve_per_service_call_history_providers(
-        self,
-        *,
-        session: AgentSession | None,
-        options: Mapping[str, Any] | None,
-        service_stores_history: bool,
-    ) -> list[HistoryProvider]:
-        history_providers = self._get_history_providers()
-        if not self.require_per_service_call_history_persistence or not history_providers:
-            return []
-
-        conversation_id = (
-            session.service_session_id
-            if session and session.service_session_id
-            else cast(str | None, (options or {}).get("conversation_id") or self.default_options.get("conversation_id"))
-        )
-        if service_stores_history:
-            return []
-
-        if conversation_id is not None:
-            raise AgentInvalidRequestException(
-                "require_per_service_call_history_persistence cannot be used "
-                "with an existing service-managed conversation."
-            )
-        return history_providers
-
     async def __aexit__(
         self,
         exc_type: type[BaseException] | None,
@@ -930,9 +885,97 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
             When stream=True: A ResponseStream of AgentResponseUpdate items with
                 ``get_final_response()`` for the final AgentResponse.
         """
+        if not stream:
 
-        async def _prepare_run_context() -> _RunContext:
-            return await self._prepare_run_context(
+            async def _run_non_streaming() -> AgentResponse[Any]:
+                ctx = await self._prepare_run_context(
+                    messages=messages,
+                    session=session,
+                    tools=tools,
+                    options=options,
+                    compaction_strategy=compaction_strategy,
+                    tokenizer=tokenizer,
+                    function_invocation_kwargs=function_invocation_kwargs,
+                    client_kwargs=client_kwargs,
+                )
+                response = cast(
+                    ChatResponse[Any],
+                    await self.client.get_response(  # type: ignore
+                        messages=ctx["session_messages"],
+                        stream=False,
+                        options=ctx["chat_options"],  # type: ignore[reportArgumentType]
+                        compaction_strategy=ctx["compaction_strategy"],
+                        tokenizer=ctx["tokenizer"],
+                        function_invocation_kwargs=ctx["function_invocation_kwargs"],
+                        client_kwargs=ctx["client_kwargs"],
+                    ),
+                )
+
+                if not response:
+                    raise AgentInvalidResponseException("Chat client did not return a response.")
+
+                await self._finalize_response(
+                    response=response,
+                    agent_name=ctx["agent_name"],
+                    session=ctx["session"],
+                    session_context=ctx["session_context"],
+                )
+                response_format = ctx["chat_options"].get("response_format")
+                if not (
+                    response_format is not None
+                    and isinstance(response_format, type)
+                    and issubclass(response_format, BaseModel)
+                ):
+                    response_format = None
+
+                return AgentResponse(
+                    messages=response.messages,
+                    response_id=response.response_id,
+                    created_at=response.created_at,
+                    usage_details=response.usage_details,
+                    value=response.value,
+                    response_format=response_format,
+                    continuation_token=response.continuation_token,
+                    raw_representation=response,
+                    additional_properties=response.additional_properties,
+                )
+
+            return _run_non_streaming()
+
+        # Use a holder to capture the context created during stream initialization
+        ctx_holder: dict[str, _RunContext | None] = {"ctx": None}
+
+        async def _post_hook(response: AgentResponse) -> None:
+            ctx = ctx_holder["ctx"]
+            if ctx is None:
+                return  # No context available (shouldn't happen in normal flow)
+
+            # Update thread with conversation_id derived from streaming raw updates.
+            # Using response_id here can break function-call continuation for APIs
+            # where response IDs are not valid conversation handles.
+            conversation_id = self._extract_conversation_id_from_streaming_response(response)
+            # Ensure author names are set for all messages
+            for message in response.messages:
+                if message.author_name is None:
+                    message.author_name = ctx["agent_name"]
+
+            # Propagate conversation_id back to session from streaming updates.
+            # For Responses-style APIs this can rotate every turn (response_id-based continuation),
+            # so refresh when a newer value is returned.
+            sess = ctx["session"]
+            if sess and conversation_id and sess.service_session_id != conversation_id:
+                sess.service_session_id = conversation_id
+
+            # Run after_run providers (reverse order)
+            session_context = ctx["session_context"]
+            session_context._response = AgentResponse(  # type: ignore[assignment]
+                messages=response.messages,
+                response_id=response.response_id,
+            )
+            await self._run_after_providers(session=ctx["session"], context=session_context)
+
+        async def _get_stream() -> ResponseStream[ChatResponseUpdate, ChatResponse[Any]]:
+            ctx_holder["ctx"] = await self._prepare_run_context(
                 messages=messages,
                 session=session,
                 tools=tools,
@@ -942,177 +985,55 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
                 function_invocation_kwargs=function_invocation_kwargs,
                 client_kwargs=client_kwargs,
             )
-
-        if not stream:
-
-            async def _run_non_streaming() -> AgentResponse[Any]:
-                ctx = await _prepare_run_context()
-                response = await self._call_chat_client(ctx, stream=False)
-                return await self._parse_non_streaming_response(ctx, response)
-
-            return _run_non_streaming()
-
-        async def _run_streaming() -> ResponseStream[AgentResponseUpdate, AgentResponse[Any]]:
-            ctx = await _prepare_run_context()
-            stream_response = self._call_chat_client(ctx, stream=True)
-            return self._parse_streaming_response(ctx, stream_response)
-
-        return cast(
-            ResponseStream[AgentResponseUpdate, AgentResponse[Any]],
-            cast(Any, ResponseStream).from_awaitable(_run_streaming()),
-        )
-
-    @overload
-    def _call_chat_client(
-        self,
-        context: _RunContext,
-        *,
-        stream: Literal[False],
-    ) -> Awaitable[ChatResponse[Any]]: ...
-
-    @overload
-    def _call_chat_client(
-        self,
-        context: _RunContext,
-        *,
-        stream: Literal[True],
-    ) -> ResponseStream[ChatResponseUpdate, ChatResponse[Any]]: ...
-
-    def _call_chat_client(
-        self,
-        context: _RunContext,
-        *,
-        stream: bool,
-    ) -> Awaitable[ChatResponse[Any]] | ResponseStream[ChatResponseUpdate, ChatResponse[Any]]:
-        """Invoke the downstream chat client for a prepared run context."""
-        if stream:
+            ctx: _RunContext = ctx_holder["ctx"]  # type: ignore[assignment]  # Safe: we just assigned it
             return self.client.get_response(  # type: ignore[call-overload, no-any-return]
-                messages=context["session_messages"],
+                messages=ctx["session_messages"],
                 stream=True,
-                options=context["chat_options"],  # type: ignore[reportArgumentType]
-                compaction_strategy=context["compaction_strategy"],
-                tokenizer=context["tokenizer"],
-                function_invocation_kwargs=context["function_invocation_kwargs"],
-                client_kwargs=context["client_kwargs"],
+                options=ctx["chat_options"],  # type: ignore[reportArgumentType]
+                compaction_strategy=ctx["compaction_strategy"],
+                tokenizer=ctx["tokenizer"],
+                function_invocation_kwargs=ctx["function_invocation_kwargs"],
+                client_kwargs=ctx["client_kwargs"],
             )
 
-        return self.client.get_response(  # type: ignore[call-overload, no-any-return]
-            messages=context["session_messages"],
-            stream=False,
-            options=context["chat_options"],  # type: ignore[reportArgumentType]
-            compaction_strategy=context["compaction_strategy"],
-            tokenizer=context["tokenizer"],
-            function_invocation_kwargs=context["function_invocation_kwargs"],
-            client_kwargs=context["client_kwargs"],
-        )
+        def _propagate_conversation_id(
+            update: AgentResponseUpdate,
+        ) -> AgentResponseUpdate:
+            """Eagerly propagate conversation_id to session as updates arrive.
 
-    async def _parse_non_streaming_response(
-        self,
-        context: _RunContext,
-        response: ChatResponse[Any],
-    ) -> AgentResponse[Any]:
-        """Finalize a non-streaming chat response into an AgentResponse."""
-        if not response:
-            raise AgentInvalidResponseException("Chat client did not return a response.")
-
-        await self._finalize_response(
-            response=response,
-            agent_name=context["agent_name"],
-            session=context["session"],
-            session_context=context["session_context"],
-            suppress_response_id=context["suppress_response_id"],
-        )
-
-        response_format = context["chat_options"].get("response_format")
-        if not (
-            response_format is not None and isinstance(response_format, type) and issubclass(response_format, BaseModel)
-        ):
-            response_format = None
-
-        return AgentResponse(
-            messages=response.messages,
-            response_id=None if context["suppress_response_id"] else response.response_id,
-            created_at=response.created_at,
-            usage_details=response.usage_details,
-            value=response.value,
-            response_format=response_format,
-            continuation_token=response.continuation_token,
-            raw_representation=response,
-            additional_properties=response.additional_properties,
-        )
-
-    def _parse_streaming_response(
-        self,
-        context: _RunContext,
-        stream_response: ResponseStream[ChatResponseUpdate, ChatResponse[Any]],
-    ) -> ResponseStream[AgentResponseUpdate, AgentResponse[Any]]:
-        """Finalize a streaming chat response into an agent response stream."""
-
-        async def _post_hook(response: AgentResponse) -> None:
-            # Update thread with conversation_id derived from streaming raw updates.
-            # Using response_id here can break function-call continuation for APIs
-            # where response IDs are not valid conversation handles.
-            conversation_id = self._extract_conversation_id_from_streaming_response(response)
-
-            for message in response.messages:
-                if message.author_name is None:
-                    message.author_name = context["agent_name"]
-
-            session = context["session"]
-            if (
-                session
-                and conversation_id
-                and not is_local_history_conversation_id(conversation_id)
-                and session.service_session_id != conversation_id
-            ):
-                session.service_session_id = conversation_id
-
-            suppress_response_id = context["suppress_response_id"]
-            session_context = context["session_context"]
-            session_context._response = AgentResponse(  # type: ignore[assignment]
-                messages=response.messages,
-                response_id=None if suppress_response_id else response.response_id,
-            )
-            await self._run_after_providers(session=session, context=session_context)
-
-        def _propagate_conversation_id(update: AgentResponseUpdate) -> AgentResponseUpdate:
-            """Eagerly propagate conversation_id to session as updates arrive."""
-            session = context["session"]
+            This ensures session.service_session_id is set even when the user
+            only iterates the stream without calling get_final_response().
+            """
             if session is None:
                 return update
             raw = update.raw_representation
-            conversation_id = getattr(raw, "conversation_id", None) if raw else None
-            if (
-                isinstance(conversation_id, str)
-                and conversation_id
-                and not is_local_history_conversation_id(conversation_id)
-                and session.service_session_id != conversation_id
-            ):
-                session.service_session_id = conversation_id
-            return update
-
-        def _suppress_response_id(update: AgentResponseUpdate) -> AgentResponseUpdate:
-            """Hide raw service response ids when local per-service-call persistence owns continuation."""
-            update.response_id = None
+            conv_id = getattr(raw, "conversation_id", None) if raw else None
+            if isinstance(conv_id, str) and conv_id and session.service_session_id != conv_id:
+                session.service_session_id = conv_id
             return update
 
         def _finalizer(updates: Sequence[AgentResponseUpdate]) -> AgentResponse[Any]:
-            return self._finalize_response_updates(
-                updates,
-                response_format=context["chat_options"].get("response_format"),
+            ctx = ctx_holder["ctx"]
+            rf = (
+                ctx.get("chat_options", {}).get("response_format")
+                if ctx
+                else (options.get("response_format") if options else None)  # type: ignore[union-attr]
             )
+            return self._finalize_response_updates(updates, response_format=rf)
 
-        stream = stream_response.map(
-            transform=partial(
-                map_chat_to_agent_update,
-                agent_name=self.name,
-            ),
-            finalizer=_finalizer,
+        return (
+            ResponseStream
+            .from_awaitable(_get_stream())  # type: ignore[reportUnknownMemberType]
+            .map(
+                transform=partial(
+                    map_chat_to_agent_update,
+                    agent_name=self.name,
+                ),
+                finalizer=_finalizer,
+            )
+            .with_transform_hook(_propagate_conversation_id)
+            .with_result_hook(_post_hook)
         )
-        if context["suppress_response_id"]:
-            stream = stream.with_transform_hook(_suppress_response_id)
-
-        return stream.with_transform_hook(_propagate_conversation_id).with_result_hook(_post_hook)
 
     def _finalize_response_updates(
         self,
@@ -1190,12 +1111,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         if active_session is None and self.context_providers:
             active_session = AgentSession()
 
-        per_service_call_history_providers = self._resolve_per_service_call_history_providers(
-            session=active_session,
-            options=opts,
-            service_stores_history=bool(store_),
-        )
-
         session_context, chat_options = await self._prepare_session_and_messages(
             session=active_session,
             input_messages=input_messages,
@@ -1276,43 +1191,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         effective_client_kwargs = dict(client_kwargs) if client_kwargs is not None else {}
         if active_session is not None:
             effective_client_kwargs["session"] = active_session
-        if per_service_call_history_providers and active_session is not None:
-            per_service_call_history_middleware = PerServiceCallHistoryPersistingMiddleware(
-                agent=self,
-                session=active_session,
-                providers=per_service_call_history_providers,
-            )
-            existing_middleware = effective_client_kwargs.get("middleware")
-            if isinstance(existing_middleware, Sequence) and not isinstance(existing_middleware, (str, bytes)):
-                effective_client_kwargs["middleware"] = [per_service_call_history_middleware, *existing_middleware]
-            elif existing_middleware is not None:
-                effective_client_kwargs["middleware"] = [
-                    per_service_call_history_middleware,
-                    cast(MiddlewareTypes, existing_middleware),
-                ]
-            else:
-                effective_client_kwargs["middleware"] = [per_service_call_history_middleware]
-        provider_middleware = session_context.get_middleware()
-        if provider_middleware:
-            middleware_list = categorize_middleware(provider_middleware)
-            provider_function_chat_middleware = [
-                *middleware_list["function"],
-                *middleware_list["chat"],
-            ]
-            if provider_function_chat_middleware:
-                existing_middleware = effective_client_kwargs.get("middleware")
-                if isinstance(existing_middleware, Sequence) and not isinstance(existing_middleware, (str, bytes)):
-                    effective_client_kwargs["middleware"] = [
-                        *existing_middleware,
-                        *provider_function_chat_middleware,
-                    ]
-                elif existing_middleware is not None:
-                    effective_client_kwargs["middleware"] = [
-                        cast(MiddlewareTypes, existing_middleware),
-                        *provider_function_chat_middleware,
-                    ]
-                else:
-                    effective_client_kwargs["middleware"] = provider_function_chat_middleware
 
         return {
             "session": active_session,
@@ -1320,7 +1198,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
             "input_messages": input_messages,
             "session_messages": session_messages,
             "agent_name": agent_name,
-            "suppress_response_id": bool(per_service_call_history_providers),
             "chat_options": co,
             "compaction_strategy": compaction_strategy or self.compaction_strategy,
             "tokenizer": tokenizer or self.tokenizer,
@@ -1334,7 +1211,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         agent_name: str,
         session: AgentSession | None,
         session_context: SessionContext,
-        suppress_response_id: bool = False,
     ) -> None:
         """Finalize response by setting author names and running after_run providers.
 
@@ -1343,7 +1219,6 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
             agent_name: The name of the agent to set as author.
             session: The conversation session.
             session_context: The invocation context.
-            suppress_response_id: When True, omit the raw service response ID from the public response.
         """
         # Ensure that the author name is set for each message in the response.
         for message in response.messages:
@@ -1353,18 +1228,13 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
         # Propagate conversation_id back to session (e.g. thread ID from Assistants API).
         # For Responses-style APIs this can rotate every turn (response_id-based continuation),
         # so refresh when a newer value is returned.
-        if (
-            session
-            and response.conversation_id
-            and not is_local_history_conversation_id(response.conversation_id)
-            and session.service_session_id != response.conversation_id
-        ):
+        if session and response.conversation_id and session.service_session_id != response.conversation_id:
             session.service_session_id = response.conversation_id
 
         # Set the response on the context for after_run providers
         session_context._response = AgentResponse(  # type: ignore[assignment]
             messages=response.messages,
-            response_id=None if suppress_response_id else response.response_id,
+            response_id=response.response_id,
         )
 
         # Run after_run providers (reverse order)
@@ -1414,15 +1284,9 @@ class RawAgent(BaseAgent, Generic[OptionsCoT]):  # type: ignore[misc]
             options=options or {},
         )
 
-        per_service_call_history_required = self.require_per_service_call_history_persistence and bool(
-            self._get_history_providers()
-        )
-
-        # Run before_run providers (forward order, skip HistoryProvider when per-service-call persistence owns history)
+        # Run before_run providers (forward order, skip BaseHistoryProvider with load_messages=False)
         for provider in self.context_providers:
-            if per_service_call_history_required and isinstance(provider, HistoryProvider):
-                continue
-            if isinstance(provider, HistoryProvider) and not provider.load_messages:
+            if isinstance(provider, BaseHistoryProvider) and not provider.load_messages:
                 continue
             if provider_session is None:
                 raise RuntimeError("Provider session must be available when context providers are configured.")
@@ -1687,9 +1551,8 @@ class Agent(
         description: str | None = None,
         tools: ToolTypes | Callable[..., Any] | Sequence[ToolTypes | Callable[..., Any]] | None = None,
         default_options: OptionsCoT | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
         additional_properties: MutableMapping[str, Any] | None = None,
@@ -1705,7 +1568,6 @@ class Agent(
             default_options=default_options,
             context_providers=context_providers,
             middleware=middleware,
-            require_per_service_call_history_persistence=require_per_service_call_history_persistence,
             compaction_strategy=compaction_strategy,
             tokenizer=tokenizer,
             additional_properties=additional_properties,

python/packages/core/agent_framework/_clients.py

@@ -572,7 +572,6 @@ class BaseChatClient(SerializationMixin, ABC, Generic[OptionsCoT]):
         default_options: OptionsCoT | Mapping[str, Any] | None = None,
         context_providers: Sequence[Any] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         function_invocation_configuration: FunctionInvocationConfiguration | None = None,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
@@ -597,10 +596,6 @@ class BaseChatClient(SerializationMixin, ABC, Generic[OptionsCoT]):
                 and dict literals are accepted without specialized option typing.
             context_providers: Context providers to include during agent invocation.
             middleware: List of middleware to intercept agent and function invocations.
-            require_per_service_call_history_persistence: Whether to require per-service-call
-                chat history persistence. When enabled, history providers are invoked around
-                each model call instead of once per ``run()`` when the service is not already
-                storing history.
             function_invocation_configuration: Optional function invocation configuration override.
             compaction_strategy: Optional agent-level compaction override. When omitted,
                 client-level compaction defaults remain in effect for each call.
@@ -641,7 +636,6 @@ class BaseChatClient(SerializationMixin, ABC, Generic[OptionsCoT]):
             "default_options": cast(Any, default_options),
             "context_providers": context_providers,
             "middleware": middleware,
-            "require_per_service_call_history_persistence": require_per_service_call_history_persistence,
             "compaction_strategy": compaction_strategy,
             "tokenizer": tokenizer,
             "additional_properties": dict(additional_properties) if additional_properties is not None else None,
@@ -814,21 +808,22 @@ class SupportsFileSearchTool(Protocol):
 
 # region SupportsGetEmbeddings Protocol
 
-# TypeVars for the Protocol
+# Contravariant TypeVars for the Protocol
 EmbeddingInputContraT = TypeVar(
     "EmbeddingInputContraT",
     default="str",
     contravariant=True,
 )
-EmbeddingProtocolOptionsT = TypeVar(
-    "EmbeddingProtocolOptionsT",
+EmbeddingOptionsContraT = TypeVar(
+    "EmbeddingOptionsContraT",
     bound=TypedDict,  # type: ignore[valid-type]
     default="EmbeddingGenerationOptions",
+    contravariant=True,
 )
 
 
 @runtime_checkable
-class SupportsGetEmbeddings(Protocol[EmbeddingInputContraT, EmbeddingT, EmbeddingProtocolOptionsT]):
+class SupportsGetEmbeddings(Protocol[EmbeddingInputContraT, EmbeddingT, EmbeddingOptionsContraT]):
     """Protocol for an embedding client that can generate embeddings.
 
     This protocol enables duck-typing for embedding generation. Any class that
@@ -855,8 +850,8 @@ class SupportsGetEmbeddings(Protocol[EmbeddingInputContraT, EmbeddingT, Embeddin
         self,
         values: Sequence[EmbeddingInputContraT],
         *,
-        options: EmbeddingProtocolOptionsT | None = None,
-    ) -> Awaitable[GeneratedEmbeddings[EmbeddingT, EmbeddingProtocolOptionsT]]:
+        options: EmbeddingOptionsContraT | None = None,
+    ) -> Awaitable[GeneratedEmbeddings[EmbeddingT]]:
         """Generate embeddings for the given values.
 
         Args:

python/packages/core/agent_framework/_compaction.py

@@ -15,7 +15,7 @@ from typing import (
     runtime_checkable,
 )
 
-from ._sessions import ContextProvider
+from ._sessions import BaseContextProvider
 from ._types import ChatResponse, Content, Message
 
 if TYPE_CHECKING:
@@ -1152,7 +1152,7 @@ async def apply_compaction(
 COMPACTION_STATE_KEY: Final[str] = "_compaction_messages"
 
 
-class CompactionProvider(ContextProvider):
+class CompactionProvider(BaseContextProvider):
     """Context provider that compacts messages before and after agent runs.
 
     This provider accepts two separate strategies:

python/packages/core/agent_framework/_evaluation.py

@@ -96,7 +96,6 @@ class ConversationSplitter(Protocol):
             # Fallback: split at last user message
             return EvalItem._split_last_turn_static(conversation)
 
-
         item.split_messages(split=split_before_memory)
     """
 
@@ -469,7 +468,10 @@ class EvalResults:
         """
         if not self.all_passed:
             errored = (self.result_counts or {}).get("errored", 0)
-            detail = msg or (f"Eval run {self.run_id} {self.status}: {self.passed} passed, {self.failed} failed.")
+            detail = msg or (
+                f"Eval run {self.run_id} {self.status}: "
+                f"{self.passed} passed, {self.failed} failed."
+            )
             if errored:
                 detail += f" {errored} errored."
             if self.report_url:
@@ -1186,7 +1188,8 @@ def _coerce_result(value: Any, check_name: str) -> CheckResult:
                 score = float(d["score"])
             except (TypeError, ValueError) as exc:
                 raise TypeError(
-                    f"Function evaluator '{check_name}' returned dict with non-numeric 'score' value: {d['score']!r}"
+                    f"Function evaluator '{check_name}' returned dict with non-numeric 'score' value:"
+                    f" {d['score']!r}"
                 ) from exc
             # Honour an explicit 'passed' override; otherwise threshold-based.
             passed = bool(d["passed"]) if "passed" in d else score >= float(d.get("threshold", 0.5))

python/packages/core/agent_framework/_sessions.py

@@ -4,8 +4,8 @@
 
 This module provides the core types for the context provider pipeline:
 - SessionContext: Per-invocation state passed through providers
-- ContextProvider: Base class for context providers
-- HistoryProvider: Base class for history storage providers
+- BaseContextProvider: Base class for context providers (renamed to ContextProvider in PR2)
+- BaseHistoryProvider: Base class for history storage providers (renamed to HistoryProvider in PR2)
 - AgentSession: Lightweight session state container
 - InMemoryHistoryProvider: Built-in in-memory history provider
 """
@@ -13,42 +13,21 @@ This module provides the core types for the context provider pipeline:
 from __future__ import annotations
 
 import copy
-import sys
 import uuid
 from abc import abstractmethod
-from collections.abc import Awaitable, Callable, Mapping, Sequence
-from typing import TYPE_CHECKING, Any, ClassVar, TypeGuard, cast
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, ClassVar, cast
 
-if sys.version_info >= (3, 13):
-    from warnings import deprecated  # type: ignore # pragma: no cover
-else:
-    from typing_extensions import deprecated  # type: ignore # pragma: no cover
-
-from ._middleware import ChatContext, ChatMiddleware
-from ._types import AgentResponse, ChatResponse, Message, ResponseStream
-from .exceptions import ChatClientInvalidResponseException
+from ._types import AgentResponse, Message
 
 if TYPE_CHECKING:
     from ._agents import SupportsAgentRun
-    from ._middleware import MiddlewareTypes
 
 
 # Registry of known types for state deserialization
 _STATE_TYPE_REGISTRY: dict[str, type] = {}
 
 
-def _is_middleware_sequence(
-    middleware: MiddlewareTypes | Sequence[MiddlewareTypes],
-) -> TypeGuard[Sequence[MiddlewareTypes]]:
-    return isinstance(middleware, Sequence) and not isinstance(middleware, (str, bytes))
-
-
-def _is_single_middleware(
-    middleware: MiddlewareTypes | Sequence[MiddlewareTypes],
-) -> TypeGuard[MiddlewareTypes]:
-    return not _is_middleware_sequence(middleware)
-
-
 def register_state_type(cls: type) -> None:
     """Register a type for automatic deserialization in session state.
 
@@ -152,8 +131,6 @@ class SessionContext:
             Maintains insertion order (provider execution order).
         instructions: Additional instructions added by providers.
         tools: Additional tools added by providers.
-        middleware: Dict mapping source_id -> chat/function middleware added by that provider.
-            Maintains insertion order (provider execution order).
         response: After invocation, contains the full AgentResponse, should not be changed.
         options: Options passed to agent.run() - read-only, for reflection only.
         metadata: Shared metadata dictionary for cross-provider communication.
@@ -168,7 +145,6 @@ class SessionContext:
         context_messages: dict[str, list[Message]] | None = None,
         instructions: list[str] | None = None,
         tools: list[Any] | None = None,
-        middleware: dict[str, list[MiddlewareTypes]] | None = None,
         options: dict[str, Any] | None = None,
         metadata: dict[str, Any] | None = None,
     ):
@@ -181,7 +157,6 @@ class SessionContext:
             context_messages: Pre-populated context messages by source.
             instructions: Pre-populated instructions.
             tools: Pre-populated tools.
-            middleware: Pre-populated chat/function middleware by source.
             options: Options from agent.run() - read-only for providers.
             metadata: Shared metadata for cross-provider communication.
         """
@@ -191,10 +166,6 @@ class SessionContext:
         self.context_messages: dict[str, list[Message]] = context_messages or {}
         self.instructions: list[str] = instructions or []
         self.tools: list[Any] = tools or []
-        self.middleware: dict[str, list[MiddlewareTypes]] = {}
-        if middleware:
-            for source_id, provider_middleware in middleware.items():
-                self.extend_middleware(source_id, provider_middleware)
         self._response: AgentResponse | None = None
         self.options: dict[str, Any] = options or {}
         self.metadata: dict[str, Any] = metadata or {}
@@ -265,40 +236,6 @@ class SessionContext:
                     additional_properties["context_source"] = source_id
         self.tools.extend(tools)
 
-    def extend_middleware(
-        self,
-        source_id: str,
-        middleware: MiddlewareTypes | Sequence[MiddlewareTypes],
-    ) -> None:
-        """Add middleware to be applied for this invocation.
-
-        Args:
-            source_id: The provider source_id adding this middleware.
-            middleware: A single chat/function middleware object/callable or sequence of middleware.
-        """
-        from ._middleware import categorize_middleware
-        from .exceptions import MiddlewareException
-
-        if _is_middleware_sequence(middleware):
-            middleware_items = list(middleware)
-        elif _is_single_middleware(middleware):
-            middleware_items = [middleware]
-        else:
-            raise TypeError("middleware must be a middleware object or a sequence of middleware objects.")
-        middleware_list = categorize_middleware(middleware_items)
-        if middleware_list["agent"]:
-            raise MiddlewareException("Context providers may only add chat or function middleware.")
-        if source_id not in self.middleware:
-            self.middleware[source_id] = []
-        self.middleware[source_id].extend(middleware_items)
-
-    def get_middleware(self) -> list[MiddlewareTypes]:
-        """Get provider-added chat/function middleware in provider execution order."""
-        result: list[MiddlewareTypes] = []
-        for middleware_items in self.middleware.values():
-            result.extend(middleware_items)
-        return result
-
     def get_messages(
         self,
         *,
@@ -335,12 +272,17 @@ class SessionContext:
         return result
 
 
-class ContextProvider:
-    """Base class for context providers.
+class BaseContextProvider:
+    """Base class for context providers (hooks pattern).
 
     Context providers participate in the context engineering pipeline,
     adding context before model invocation and processing responses after.
 
+    Note:
+        This class uses a temporary name prefixed with ``_`` to avoid collision
+        with the existing ``ContextProvider`` in ``_memory.py``. It will be
+        renamed to ``ContextProvider`` in PR2 when the old class is removed.
+
     Attributes:
         source_id: Unique identifier for this provider instance (required).
             Used for message/tool attribution so other providers can filter.
@@ -370,7 +312,7 @@ class ContextProvider:
         Args:
             agent: The agent running this invocation.
             session: The current session.
-            context: The invocation context - add messages/instructions/tools/chat/function middleware here.
+            context: The invocation context - add messages/instructions/tools here.
             state: The provider-scoped mutable state dict for this provider.
                 Full cross-provider state remains available at ``session.state``.
         """
@@ -397,7 +339,7 @@ class ContextProvider:
         """
 
 
-class HistoryProvider(ContextProvider):
+class BaseHistoryProvider(BaseContextProvider):
     """Base class for conversation history storage providers.
 
     A single class configurable for different use cases:
@@ -405,6 +347,10 @@ class HistoryProvider(ContextProvider):
     - Audit/logging storage (stores only, doesn't load)
     - Evaluation storage (stores only for later analysis)
 
+    Note:
+        This class uses a temporary name prefixed with ``_`` to avoid collision
+        with existing types. It will be renamed to ``HistoryProvider`` in PR2.
+
     Subclasses only need to implement ``get_messages()`` and ``save_messages()``.
     The default ``before_run``/``after_run`` handle loading and storing based on
     configuration flags. Override them for custom behavior.
@@ -521,207 +467,6 @@ class HistoryProvider(ContextProvider):
             await self.save_messages(context.session_id, messages_to_store, state=state)
 
 
-LOCAL_HISTORY_CONVERSATION_ID = "agent_framework_local_history_persistence"
-
-
-def is_local_history_conversation_id(conversation_id: str | None) -> bool:
-    """Return whether a conversation id is the local history-persistence sentinel."""
-    return conversation_id == LOCAL_HISTORY_CONVERSATION_ID
-
-
-def _response_contains_follow_up_request(response: ChatResponse) -> bool:
-    """Return whether a response requires another model call in the current run."""
-    return any(
-        item.type in {"function_call", "function_approval_request"}
-        for message in response.messages
-        for item in message.contents
-    )
-
-
-def _split_service_call_messages(messages: Sequence[Message]) -> tuple[list[Message], dict[str, list[Message]]]:
-    """Split service-call messages into input messages and attributed context messages."""
-    input_messages: list[Message] = []
-    context_messages: dict[str, list[Message]] = {}
-    for message in messages:
-        attribution = message.additional_properties.get("_attribution")
-        if isinstance(attribution, Mapping):
-            attribution_mapping = cast(Mapping[str, Any], attribution)
-            source_id = attribution_mapping.get("source_id")
-            if isinstance(source_id, str):
-                context_messages.setdefault(source_id, []).append(message)
-                continue
-        input_messages.append(message)
-    return input_messages, context_messages
-
-
-class PerServiceCallHistoryPersistingMiddleware(ChatMiddleware):
-    """Persist local chat history after each service call when history is framework-managed.
-
-    This middleware runs around each model call when
-    ``require_per_service_call_history_persistence`` is enabled. It loads history providers
-    before the model call, persists them after the model call, and uses a local
-    sentinel conversation id so the function loop follows the existing
-    service-managed branch without forwarding that sentinel to the leaf client.
-    """
-
-    def __init__(
-        self,
-        *,
-        agent: SupportsAgentRun,
-        session: AgentSession,
-        providers: Sequence[HistoryProvider],
-    ) -> None:
-        """Initialize the middleware.
-
-        Args:
-            agent: The agent that owns the history providers.
-            session: The active session for the current run.
-            providers: The history providers participating in per-service-call persistence.
-        """
-        self._agent = agent
-        self._session = session
-        self._providers = list(providers)
-
-    async def _prepare_service_call_context(self, messages: Sequence[Message]) -> SessionContext:
-        """Create a per-call SessionContext and load history providers into it."""
-        input_messages, context_messages = _split_service_call_messages(messages)
-        service_call_context = SessionContext(
-            session_id=self._session.session_id,
-            service_session_id=None,
-            input_messages=list(input_messages),
-        )
-        for source_id, source_messages in context_messages.items():
-            service_call_context.extend_messages(source_id, source_messages)
-        for provider in self._providers:
-            if not provider.load_messages:
-                continue
-            await provider.before_run(
-                agent=self._agent,
-                session=self._session,
-                context=service_call_context,
-                state=self._session.state.setdefault(provider.source_id, {}),
-            )
-        return service_call_context
-
-    async def _persist_service_call_response(
-        self,
-        *,
-        service_call_context: SessionContext,
-        response: ChatResponse,
-    ) -> None:
-        """Persist a single model-call response through the configured history providers."""
-        service_call_context._response = AgentResponse(  # type: ignore[assignment]
-            messages=response.messages,
-            response_id=None,
-        )
-        for provider in reversed(self._providers):
-            await provider.after_run(
-                agent=self._agent,
-                session=self._session,
-                context=service_call_context,
-                state=self._session.state.setdefault(provider.source_id, {}),
-            )
-
-    def _strip_local_conversation_id(self, context: ChatContext) -> None:
-        """Remove the local sentinel before the leaf chat client is invoked."""
-        if is_local_history_conversation_id(cast(str | None, context.kwargs.get("conversation_id"))):
-            context.kwargs.pop("conversation_id", None)
-
-        if context.options is None:
-            return
-
-        mutable_options = dict(context.options)
-        if is_local_history_conversation_id(cast(str | None, mutable_options.get("conversation_id"))):
-            mutable_options.pop("conversation_id", None)
-        context.options = mutable_options
-
-    async def _finalize_response(
-        self,
-        *,
-        service_call_context: SessionContext,
-        response: ChatResponse,
-    ) -> ChatResponse:
-        """Persist a model response and apply the local follow-up sentinel when needed."""
-        if response.conversation_id is not None and not is_local_history_conversation_id(response.conversation_id):
-            raise ChatClientInvalidResponseException(
-                "require_per_service_call_history_persistence cannot be used "
-                "when the chat client returns a real conversation_id."
-            )
-
-        await self._persist_service_call_response(
-            service_call_context=service_call_context,
-            response=response,
-        )
-        if _response_contains_follow_up_request(response):
-            response.mark_internal_conversation_id()
-            response.conversation_id = LOCAL_HISTORY_CONVERSATION_ID
-        return response
-
-    async def process(self, context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-        """Load and persist history providers around a single model call.
-
-        Args:
-            context: The chat invocation context for the current model call.
-            call_next: The next middleware or the leaf chat client.
-
-        Raises:
-            ChatClientInvalidResponseException: If the leaf client returns a real
-                service-managed conversation id while local per-service-call persistence is enabled.
-            ValueError: If the downstream middleware contract returns the wrong
-                result type for streaming or non-streaming execution.
-        """
-        service_call_context = await self._prepare_service_call_context(context.messages)
-        context.messages = service_call_context.get_messages(include_input=True)
-        self._strip_local_conversation_id(context)
-
-        await call_next()
-
-        if context.result is None:
-            return
-
-        if context.stream:
-            if not isinstance(context.result, ResponseStream):
-                raise ValueError("Streaming chat middleware requires a ResponseStream result.")
-            context.result = context.result.with_result_hook(
-                lambda response: self._finalize_response(
-                    service_call_context=service_call_context,
-                    response=response,
-                )
-            )
-            return
-
-        if isinstance(context.result, ResponseStream):
-            raise ValueError("Non-streaming chat middleware requires a ChatResponse result.")
-        context.result = await self._finalize_response(
-            service_call_context=service_call_context,
-            response=context.result,
-        )
-
-
-@deprecated(
-    "BaseContextProvider is deprecated. Use ContextProvider instead.",
-    category=DeprecationWarning,
-)
-class BaseContextProvider(ContextProvider):
-    """Deprecated alias for :class:`ContextProvider`.
-
-    .. deprecated::
-        BaseContextProvider is deprecated. Use :class:`ContextProvider` instead.
-    """
-
-
-@deprecated(
-    "BaseHistoryProvider is deprecated. Use HistoryProvider instead.",
-    category=DeprecationWarning,
-)
-class BaseHistoryProvider(HistoryProvider):
-    """Deprecated alias for :class:`HistoryProvider`.
-
-    .. deprecated::
-        BaseHistoryProvider is deprecated. Use :class:`HistoryProvider` instead.
-    """
-
-
 class AgentSession:
     """A conversation session with an agent.
 
@@ -790,7 +535,7 @@ class AgentSession:
         return session
 
 
-class InMemoryHistoryProvider(HistoryProvider):
+class InMemoryHistoryProvider(BaseHistoryProvider):
     """Built-in history provider that stores messages in session.state.
 
     Messages are stored in ``state["messages"]`` as a list of

python/packages/core/agent_framework/_skills.py

@@ -36,7 +36,7 @@ from pathlib import Path, PurePosixPath
 from typing import TYPE_CHECKING, Any, ClassVar, Final, Protocol, runtime_checkable
 
 from ._feature_stage import ExperimentalFeature, experimental
-from ._sessions import ContextProvider
+from ._sessions import BaseContextProvider
 from ._tools import FunctionTool
 
 if TYPE_CHECKING:
@@ -519,7 +519,7 @@ SCRIPT_RUNNER_INSTRUCTIONS: Final[str] = (
 
 
 @experimental(feature_id=ExperimentalFeature.SKILLS)
-class SkillsProvider(ContextProvider):
+class SkillsProvider(BaseContextProvider):
     """Context provider that advertises skills and exposes skill tools.
 
     Supports both **file-based** skills (discovered from ``SKILL.md`` files)

python/packages/core/agent_framework/_tools.py

@@ -1688,34 +1688,6 @@ def _update_conversation_id(
         options["conversation_id"] = conversation_id
 
 
-def _update_continuation_state(
-    kwargs: dict[str, Any],
-    response: ChatResponse[Any],
-    *,
-    session: AgentSession | None,
-    options: dict[str, Any] | None = None,
-) -> None:
-    """Update in-flight and persisted continuation state from a response."""
-    conversation_id = response.conversation_id
-    if conversation_id is None:
-        return
-
-    _update_conversation_id(kwargs, conversation_id, options)
-    if (
-        session is not None
-        and not response.has_internal_conversation_id()
-        and session.service_session_id != conversation_id
-    ):
-        session.service_session_id = conversation_id
-
-
-def _clear_internal_conversation_id(response: ChatResponse[Any]) -> ChatResponse[Any]:
-    if response.has_internal_conversation_id():
-        response.conversation_id = None
-        response.clear_internal_conversation_id()
-    return response
-
-
 def _extract_tools(
     options: dict[str, Any] | None,
 ) -> ToolTypes | Callable[..., Any] | Sequence[ToolTypes | Callable[..., Any]] | None:
@@ -2234,14 +2206,9 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
                         ),
                     )
                     aggregated_usage = add_usage_details(aggregated_usage, response.usage_details)
-                    _update_continuation_state(
-                        filtered_kwargs,
-                        response,
-                        session=invocation_session,
-                        options=mutable_options,
-                    )
 
                     if response.conversation_id is not None:
+                        _update_conversation_id(filtered_kwargs, response.conversation_id, mutable_options)
                         prepped_messages = []
 
                     result = await _process_function_requests(
@@ -2256,7 +2223,7 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
                     )
                     if result.get("action") == "return":
                         response.usage_details = aggregated_usage
-                        return _clear_internal_conversation_id(response)
+                        return response
                     total_function_calls += result.get("function_call_count", 0)
                     if result.get("action") == "stop":
                         # Error threshold reached: force a final non-tool turn so
@@ -2312,17 +2279,11 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
                     ),
                 )
                 aggregated_usage = add_usage_details(aggregated_usage, response.usage_details)
-                _update_continuation_state(
-                    filtered_kwargs,
-                    response,
-                    session=invocation_session,
-                    options=mutable_options,
-                )
                 response.usage_details = aggregated_usage
                 if fcc_messages:
                     for msg in reversed(fcc_messages):
                         response.messages.insert(0, msg)
-                return _clear_internal_conversation_id(response)
+                return response
 
             return _get_response()
 
@@ -2382,12 +2343,6 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
                 # Get the finalized response from the inner stream
                 # This triggers the inner stream's finalizer and result hooks
                 response = await inner_stream.get_final_response()
-                _update_continuation_state(
-                    filtered_kwargs,
-                    response,
-                    session=invocation_session,
-                    options=mutable_options,
-                )
 
                 if not any(
                     item.type in ("function_call", "function_approval_request")
@@ -2397,6 +2352,7 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
                     return
 
                 if response.conversation_id is not None:
+                    _update_conversation_id(filtered_kwargs, response.conversation_id, mutable_options)
                     prepped_messages = []
 
                 result = await _process_function_requests(
@@ -2474,13 +2430,7 @@ class FunctionInvocationLayer(Generic[OptionsCoT]):
             async for update in final_inner_stream:
                 yield update
             # Finalize the inner stream to trigger its hooks
-            final_response = await final_inner_stream.get_final_response()
-            _update_continuation_state(
-                filtered_kwargs,
-                final_response,
-                session=invocation_session,
-                options=mutable_options,
-            )
+            await final_inner_stream.get_final_response()
 
         def _finalize(updates: Sequence[ChatResponseUpdate]) -> ChatResponse[Any]:
             # Note: stream_result_hooks are already run via inner stream's get_final_response()

python/packages/core/agent_framework/_types.py

@@ -1380,13 +1380,6 @@ class Content:
 
     def _add_text_reasoning_content(self, other: Content) -> Content:
         """Add two TextReasoningContent instances."""
-        # Ensure we do not silently merge contents with conflicting ids
-        if self.id and other.id and self.id != other.id:
-            raise AdditionItemMismatch(
-                f"Cannot add text_reasoning content with different ids: {self.id!r} != {other.id!r}"
-            )
-        combined_id = self.id or other.id
-
         # Concatenate text, handling None values
         self_text = self.text or ""  # type: ignore[attr-defined]
         other_text = other.text or ""  # type: ignore[attr-defined]
@@ -1397,7 +1390,6 @@ class Content:
 
         return Content(
             "text_reasoning",
-            id=combined_id,
             text=combined_text,
             protected_data=protected_data,
             annotations=_combine_annotations(self.annotations, other.annotations),
@@ -1888,12 +1880,7 @@ def _coalesce_text_content(contents: list[Content], type_str: Literal["text", "t
             if first_new_content is None:
                 first_new_content = deepcopy(content)
             else:
-                try:
-                    first_new_content += content
-                except AdditionItemMismatch:
-                    # Different IDs means a new logical segment; flush the current one
-                    coalesced_contents.append(first_new_content)
-                    first_new_content = deepcopy(content)
+                first_new_content += content
         else:
             # skip this content, it is not of the right type
             # so write the existing one to the list and start a new one,
@@ -2001,7 +1988,6 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
     """
 
     DEFAULT_EXCLUDE: ClassVar[set[str]] = {"raw_representation", "additional_properties"}
-    _INTERNAL_CONVERSATION_ID_KEY: ClassVar[str] = "_agent_framework_internal_conversation_id"
 
     def __init__(
         self,
@@ -2070,18 +2056,6 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
         self.continuation_token = continuation_token
         self.raw_representation: Any | list[Any] | None = raw_representation
 
-    def mark_internal_conversation_id(self) -> None:
-        """Mark the current conversation_id as internal control-flow state."""
-        self.additional_properties[self._INTERNAL_CONVERSATION_ID_KEY] = True
-
-    def clear_internal_conversation_id(self) -> None:
-        """Remove the internal conversation-id marker."""
-        self.additional_properties.pop(self._INTERNAL_CONVERSATION_ID_KEY, None)
-
-    def has_internal_conversation_id(self) -> bool:
-        """Return whether conversation_id is internal control-flow state."""
-        return bool(self.additional_properties.get(self._INTERNAL_CONVERSATION_ID_KEY, False))
-
     @property
     def model_id(self) -> str | None:
         """Deprecated alias for :attr:`model`."""

python/packages/core/agent_framework/_workflows/_agent.py

@@ -14,8 +14,8 @@ from typing import TYPE_CHECKING, Any, ClassVar, Literal, cast, overload
 from .._agents import BaseAgent
 from .._sessions import (
     AgentSession,
-    ContextProvider,
-    HistoryProvider,
+    BaseContextProvider,
+    BaseHistoryProvider,
     InMemoryHistoryProvider,
     SessionContext,
 )
@@ -86,7 +86,7 @@ class WorkflowAgent(BaseAgent):
         id: str | None = None,
         name: str | None = None,
         description: str | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         **kwargs: Any,
     ) -> None:
         """Initialize the WorkflowAgent.
@@ -249,7 +249,7 @@ class WorkflowAgent(BaseAgent):
             options={},
         )
         for provider in self.context_providers:
-            if isinstance(provider, HistoryProvider) and not provider.load_messages:
+            if isinstance(provider, BaseHistoryProvider) and not provider.load_messages:
                 continue
             if provider_session is None:
                 raise RuntimeError("Provider session must be available when context providers are configured.")
@@ -314,7 +314,7 @@ class WorkflowAgent(BaseAgent):
             options={},
         )
         for provider in self.context_providers:
-            if isinstance(provider, HistoryProvider) and not provider.load_messages:
+            if isinstance(provider, BaseHistoryProvider) and not provider.load_messages:
                 continue
             if provider_session is None:
                 raise RuntimeError("Provider session must be available when context providers are configured.")

python/packages/core/agent_framework/azure/__init__.py

@@ -15,10 +15,6 @@ _IMPORTS: dict[str, tuple[str, str]] = {
     "AzureAISearchContextProvider": ("agent_framework_azure_ai_search", "agent-framework-azure-ai-search"),
     "AzureAISearchSettings": ("agent_framework_azure_ai_search", "agent-framework-azure-ai-search"),
     "AzureAISettings": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureAIInferenceEmbeddingClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureAIInferenceEmbeddingOptions": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureAIInferenceEmbeddingSettings": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "RawAzureAIInferenceEmbeddingClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
     "AzureCredentialTypes": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
     "AzureTokenProvider": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
     "DurableAIAgent": ("agent_framework_durabletask", "agent-framework-durabletask"),

python/packages/core/agent_framework/azure/__init__.pyi

@@ -4,13 +4,9 @@
 # Install the relevant packages for full type support.
 
 from agent_framework_azure_ai import (
-    AzureAIInferenceEmbeddingClient,
-    AzureAIInferenceEmbeddingOptions,
-    AzureAIInferenceEmbeddingSettings,
     AzureAISettings,
     AzureCredentialTypes,
     AzureTokenProvider,
-    RawAzureAIInferenceEmbeddingClient,
 )
 from agent_framework_azure_ai_search import (
     AzureAISearchContextProvider,
@@ -30,9 +26,6 @@ __all__ = [
     "AgentCallbackContext",
     "AgentFunctionApp",
     "AgentResponseCallbackProtocol",
-    "AzureAIInferenceEmbeddingClient",
-    "AzureAIInferenceEmbeddingOptions",
-    "AzureAIInferenceEmbeddingSettings",
     "AzureAISearchContextProvider",
     "AzureAISearchSettings",
     "AzureAISettings",
@@ -42,5 +35,4 @@ __all__ = [
     "DurableAIAgentClient",
     "DurableAIAgentOrchestrationContext",
     "DurableAIAgentWorker",
-    "RawAzureAIInferenceEmbeddingClient",
 ]

python/packages/core/agent_framework/observability.py

@@ -1502,161 +1502,6 @@ class AgentTelemetryLayer:
         self.token_usage_histogram = _get_token_usage_histogram()
         self.duration_histogram = _get_duration_histogram()
 
-    def _trace_agent_invocation(
-        self,
-        *,
-        messages: AgentRunInputs | None,
-        session: AgentSession | None,
-        merged_options: Mapping[str, Any],
-        client_kwargs: Mapping[str, Any] | None,
-        stream: bool,
-        execute: Callable[[], Awaitable[AgentResponse[Any]] | ResponseStream[AgentResponseUpdate, AgentResponse[Any]]],
-    ) -> Awaitable[AgentResponse[Any]] | ResponseStream[AgentResponseUpdate, AgentResponse[Any]]:
-        """Trace an agent invocation while delegating execution to ``execute``."""
-        global OBSERVABILITY_SETTINGS
-        from ._types import ResponseStream
-
-        if not OBSERVABILITY_SETTINGS.ENABLED:
-            return execute()
-
-        provider_name = str(self.otel_provider_name)
-        merged_client_kwargs = dict(client_kwargs) if client_kwargs is not None else {}
-        attributes = _get_span_attributes(
-            operation_name=OtelAttr.AGENT_INVOKE_OPERATION,
-            provider_name=provider_name,
-            agent_id=getattr(self, "id", "unknown"),
-            agent_name=getattr(self, "name", None) or getattr(self, "id", "unknown"),
-            agent_description=getattr(self, "description", None),
-            thread_id=session.service_session_id if session else None,
-            all_options=dict(merged_options),
-            **merged_client_kwargs,
-        )
-
-        inner_response_telemetry_captured_fields: set[str] = set()
-        inner_response_telemetry_captured_fields_token = INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.set(
-            inner_response_telemetry_captured_fields
-        )
-        inner_accumulated_usage_token = INNER_ACCUMULATED_USAGE.set({})
-
-        if stream:
-            try:
-                run_result: object = execute()
-                if isinstance(run_result, ResponseStream):
-                    result_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = run_result  # pyright: ignore[reportUnknownVariableType]
-                elif isinstance(run_result, Awaitable):
-                    result_stream = ResponseStream.from_awaitable(run_result)  # type: ignore[arg-type]  # pyright: ignore[reportArgumentType]
-                else:
-                    raise RuntimeError("Streaming telemetry requires a ResponseStream result.")
-            except Exception:
-                INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
-                INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
-                raise
-
-            operation = attributes.get(OtelAttr.OPERATION, "operation")
-            span_name = attributes.get(OtelAttr.AGENT_NAME, "unknown")
-            span = get_tracer().start_span(f"{operation} {span_name}")
-            span.set_attributes(attributes)
-            if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
-                _capture_messages(
-                    span=span,
-                    provider_name=provider_name,
-                    messages=messages,
-                    system_instructions=_get_instructions_from_options(dict(merged_options)),
-                )
-
-            span_state = {"closed": False}
-            duration_state: dict[str, float] = {}
-            start_time = perf_counter()
-
-            def _close_span() -> None:
-                if span_state["closed"]:
-                    return
-                span_state["closed"] = True
-                span.end()
-
-            def _record_duration() -> None:
-                duration_state["duration"] = perf_counter() - start_time
-
-            async def _finalize_stream() -> None:
-                from ._types import AgentResponse
-
-                try:
-                    response: AgentResponse[Any] = await result_stream.get_final_response()
-                    duration = duration_state.get("duration")
-                    response_attributes = _get_response_attributes(
-                        attributes,
-                        response,
-                        capture_response_id=INNER_RESPONSE_ID_CAPTURED_FIELD
-                        not in inner_response_telemetry_captured_fields,
-                        capture_usage=INNER_USAGE_CAPTURED_FIELD not in inner_response_telemetry_captured_fields,
-                    )
-                    _apply_accumulated_usage(response_attributes, inner_response_telemetry_captured_fields)
-                    _capture_response(span=span, attributes=response_attributes, duration=duration)
-                    if (
-                        OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED
-                        and isinstance(response, AgentResponse)
-                        and response.messages
-                    ):
-                        _capture_messages(
-                            span=span,
-                            provider_name=provider_name,
-                            messages=response.messages,
-                            output=True,
-                        )
-                except Exception as exception:
-                    capture_exception(span=span, exception=exception, timestamp=time_ns())
-                finally:
-                    INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
-                    INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
-                    _close_span()
-
-            wrapped_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = result_stream.with_cleanup_hook(
-                _record_duration
-            ).with_cleanup_hook(_finalize_stream)
-            weakref.finalize(wrapped_stream, _close_span)
-            return wrapped_stream
-
-        async def _run() -> AgentResponse[Any]:
-            try:
-                with _get_span(attributes=attributes, span_name_attribute=OtelAttr.AGENT_NAME) as span:
-                    if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
-                        _capture_messages(
-                            span=span,
-                            provider_name=provider_name,
-                            messages=messages,
-                            system_instructions=_get_instructions_from_options(dict(merged_options)),
-                        )
-                    start_time_stamp = perf_counter()
-                    try:
-                        response: AgentResponse[Any] = await execute()
-                    except Exception as exception:
-                        capture_exception(span=span, exception=exception, timestamp=time_ns())
-                        raise
-                    duration = perf_counter() - start_time_stamp
-                    if response:
-                        response_attributes = _get_response_attributes(
-                            attributes,
-                            response,
-                            capture_response_id=INNER_RESPONSE_ID_CAPTURED_FIELD
-                            not in inner_response_telemetry_captured_fields,
-                            capture_usage=INNER_USAGE_CAPTURED_FIELD not in inner_response_telemetry_captured_fields,
-                        )
-                        _apply_accumulated_usage(response_attributes, inner_response_telemetry_captured_fields)
-                        _capture_response(span=span, attributes=response_attributes, duration=duration)
-                        if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and response.messages:
-                            _capture_messages(
-                                span=span,
-                                provider_name=provider_name,
-                                messages=response.messages,
-                                output=True,
-                            )
-                    return response  # type: ignore[return-value,no-any-return]
-            finally:
-                INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
-                INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
-
-        return _run()
-
     @overload
     def run(
         self,
@@ -1720,12 +1565,14 @@ class AgentTelemetryLayer:
         client_kwargs: Mapping[str, Any] | None = None,
     ) -> Awaitable[AgentResponse[Any]] | ResponseStream[AgentResponseUpdate, AgentResponse[Any]]:
         """Trace agent runs with OpenTelemetry spans and metrics."""
-        from ._types import merge_chat_options
+        global OBSERVABILITY_SETTINGS
+        from ._types import ResponseStream, merge_chat_options
 
         super_run = cast(
             "Callable[..., Awaitable[AgentResponse[Any]] | ResponseStream[AgentResponseUpdate, AgentResponse[Any]]]",
             super().run,  # type: ignore[misc]
         )
+        provider_name = str(self.otel_provider_name)
         super_run_kwargs: dict[str, Any] = {
             "messages": messages,
             "stream": stream,
@@ -1739,21 +1586,156 @@ class AgentTelemetryLayer:
         }
         if middleware is not None:
             super_run_kwargs["middleware"] = middleware
+        if not OBSERVABILITY_SETTINGS.ENABLED:
+            return super_run(**super_run_kwargs)  # type: ignore[no-any-return]
 
         default_options = dict(getattr(self, "default_options", {}))
         merged_client_kwargs = dict(client_kwargs) if client_kwargs is not None else {}
         merged_options: dict[str, Any] = merge_chat_options(
             default_options, dict(options) if options is not None else {}
         )
-        return self._trace_agent_invocation(
-            messages=messages,
-            session=session,
-            merged_options=merged_options,
-            client_kwargs=merged_client_kwargs,
-            stream=stream,
-            execute=lambda: super_run(**super_run_kwargs),
+        attributes = _get_span_attributes(
+            operation_name=OtelAttr.AGENT_INVOKE_OPERATION,
+            provider_name=provider_name,
+            agent_id=getattr(self, "id", "unknown"),
+            agent_name=getattr(self, "name", None) or getattr(self, "id", "unknown"),
+            agent_description=getattr(self, "description", None),
+            thread_id=session.service_session_id if session else None,
+            all_options=merged_options,
+            **merged_client_kwargs,
         )
 
+        inner_response_telemetry_captured_fields: set[str] = set()
+        inner_response_telemetry_captured_fields_token = INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.set(
+            inner_response_telemetry_captured_fields
+        )
+        inner_accumulated_usage_token = INNER_ACCUMULATED_USAGE.set({})
+
+        if stream:
+            try:
+                run_result: object = super_run(**super_run_kwargs)
+                if isinstance(run_result, ResponseStream):
+                    result_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = run_result  # pyright: ignore[reportUnknownVariableType]
+                elif isinstance(run_result, Awaitable):
+                    result_stream = ResponseStream.from_awaitable(run_result)  # type: ignore[arg-type]  # pyright: ignore[reportArgumentType]
+                else:
+                    raise RuntimeError("Streaming telemetry requires a ResponseStream result.")
+            except Exception:
+                INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
+                INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
+                raise
+
+            # Create span directly without trace.use_span() context attachment.
+            # Streaming spans are closed asynchronously in cleanup hooks, which run
+            # in a different async context than creation — using use_span() would
+            # cause "Failed to detach context" errors from OpenTelemetry.
+            operation = attributes.get(OtelAttr.OPERATION, "operation")
+            span_name = attributes.get(OtelAttr.AGENT_NAME, "unknown")
+            span = get_tracer().start_span(f"{operation} {span_name}")
+            span.set_attributes(attributes)
+            if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
+                _capture_messages(
+                    span=span,
+                    provider_name=provider_name,
+                    messages=messages,
+                    system_instructions=_get_instructions_from_options(merged_options),
+                )
+
+            span_state = {"closed": False}
+            duration_state: dict[str, float] = {}
+            start_time = perf_counter()
+
+            def _close_span() -> None:
+                if span_state["closed"]:
+                    return
+                span_state["closed"] = True
+                span.end()
+
+            def _record_duration() -> None:
+                duration_state["duration"] = perf_counter() - start_time
+
+            async def _finalize_stream() -> None:
+                from ._types import AgentResponse
+
+                try:
+                    response: AgentResponse[Any] = await result_stream.get_final_response()
+                    duration = duration_state.get("duration")
+                    response_attributes = _get_response_attributes(
+                        attributes,
+                        response,
+                        capture_response_id=INNER_RESPONSE_ID_CAPTURED_FIELD
+                        not in inner_response_telemetry_captured_fields,
+                        capture_usage=INNER_USAGE_CAPTURED_FIELD not in inner_response_telemetry_captured_fields,
+                    )
+                    _apply_accumulated_usage(response_attributes, inner_response_telemetry_captured_fields)
+                    _capture_response(span=span, attributes=response_attributes, duration=duration)
+                    if (
+                        OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED
+                        and isinstance(response, AgentResponse)
+                        and response.messages
+                    ):
+                        _capture_messages(
+                            span=span,
+                            provider_name=provider_name,
+                            messages=response.messages,
+                            output=True,
+                        )
+                except Exception as exception:
+                    capture_exception(span=span, exception=exception, timestamp=time_ns())
+                finally:
+                    INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
+                    INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
+                    _close_span()
+
+            # Register a weak reference callback to close the span if stream is garbage collected
+            # without being consumed. This ensures spans don't leak if users don't consume streams.
+            wrapped_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = result_stream.with_cleanup_hook(
+                _record_duration
+            ).with_cleanup_hook(_finalize_stream)
+            weakref.finalize(wrapped_stream, _close_span)
+            return wrapped_stream
+
+        async def _run() -> AgentResponse:
+            try:
+                with _get_span(attributes=attributes, span_name_attribute=OtelAttr.AGENT_NAME) as span:
+                    if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
+                        _capture_messages(
+                            span=span,
+                            provider_name=provider_name,
+                            messages=messages,
+                            system_instructions=_get_instructions_from_options(merged_options),
+                        )
+                    start_time_stamp = perf_counter()
+                    try:
+                        response: AgentResponse[Any] = await super_run(**super_run_kwargs)
+                    except Exception as exception:
+                        capture_exception(span=span, exception=exception, timestamp=time_ns())
+                        raise
+                    duration = perf_counter() - start_time_stamp
+                    if response:
+                        response_attributes = _get_response_attributes(
+                            attributes,
+                            response,
+                            capture_response_id=INNER_RESPONSE_ID_CAPTURED_FIELD
+                            not in inner_response_telemetry_captured_fields,
+                            capture_usage=INNER_USAGE_CAPTURED_FIELD not in inner_response_telemetry_captured_fields,
+                        )
+                        _apply_accumulated_usage(response_attributes, inner_response_telemetry_captured_fields)
+                        _capture_response(span=span, attributes=response_attributes, duration=duration)
+                        if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and response.messages:
+                            _capture_messages(
+                                span=span,
+                                provider_name=provider_name,
+                                messages=response.messages,
+                                output=True,
+                            )
+                    return response  # type: ignore[return-value,no-any-return]
+            finally:
+                INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
+                INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
+
+        return _run()
+
 
 # region Otel Helpers
 

python/packages/core/tests/core/test_agents.py

@@ -3,8 +3,8 @@
 import contextlib
 import inspect
 import json
-from collections.abc import AsyncIterable, Awaitable, Callable, MutableSequence, Sequence
-from typing import Any, cast
+from collections.abc import AsyncIterable, MutableSequence
+from typing import Any
 from unittest.mock import AsyncMock, MagicMock, patch
 from uuid import uuid4
 
@@ -18,29 +18,22 @@ from agent_framework import (
     AgentResponse,
     AgentResponseUpdate,
     AgentSession,
-    ChatContext,
+    BaseContextProvider,
     ChatOptions,
     ChatResponse,
     ChatResponseUpdate,
     Content,
-    ContextProvider,
     FunctionTool,
-    HistoryProvider,
-    InMemoryHistoryProvider,
     Message,
-    ResponseStream,
-    SessionContext,
     SlidingWindowStrategy,
     SupportsAgentRun,
     SupportsChatGetResponse,
     TruncationStrategy,
-    chat_middleware,
     tool,
 )
 from agent_framework._agents import _get_tool_name, _merge_options, _sanitize_agent_name
 from agent_framework._mcp import MCPTool, _build_prefixed_mcp_name, _normalize_mcp_name
 from agent_framework._middleware import FunctionInvocationContext
-from agent_framework.exceptions import AgentInvalidRequestException, ChatClientInvalidResponseException
 
 
 class _FixedTokenizer:
@@ -75,49 +68,6 @@ class _ConnectedMCPTool(MCPTool):
         raise NotImplementedError
 
 
-class _RecordingHistoryProvider(HistoryProvider):
-    def __init__(self, source_id: str = "recording_history") -> None:
-        super().__init__(source_id=source_id)
-
-    async def get_messages(
-        self,
-        session_id: str | None,
-        *,
-        state: dict[str, Any] | None = None,
-        **kwargs: Any,
-    ) -> list[Message]:
-        if state is None:
-            return []
-        state["get_call_count"] = state.get("get_call_count", 0) + 1
-        return list(cast(list[Message], state.get("messages", [])))
-
-    async def save_messages(
-        self,
-        session_id: str | None,
-        messages: Sequence[Message],
-        *,
-        state: dict[str, Any] | None = None,
-        **kwargs: Any,
-    ) -> None:
-        if state is None:
-            return
-        state["save_call_count"] = state.get("save_call_count", 0) + 1
-        state.setdefault("messages", []).extend(messages)
-
-
-class _ResponseIdRecordingHistoryProvider(_RecordingHistoryProvider):
-    async def after_run(
-        self,
-        *,
-        agent: SupportsAgentRun,
-        session: AgentSession,
-        context: SessionContext,
-        state: dict[str, Any],
-    ) -> None:
-        state.setdefault("response_ids", []).append(context.response.response_id if context.response else None)
-        await super().after_run(agent=agent, session=session, context=context, state=state)
-
-
 def test_agent_session_type(agent_session: AgentSession) -> None:
     assert isinstance(agent_session, AgentSession)
 
@@ -364,413 +314,6 @@ async def test_prepare_run_context_handles_function_kwargs(
     assert ctx["client_kwargs"]["session"] is session
 
 
-async def test_chat_agent_persists_history_per_service_call(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    session = AgentSession()
-    session.state[provider.source_id] = {
-        "messages": [
-            Message(role="user", text="Earlier question"),
-            Message(role="assistant", text="Earlier answer"),
-        ]
-    }
-    chat_client_base.run_responses = [
-        ChatResponse(
-            messages=Message(
-                role="assistant",
-                contents=[
-                    Content.from_function_call(
-                        call_id="call_1",
-                        name="lookup_weather",
-                        arguments='{"location": "Seattle"}',
-                    )
-                ],
-            ),
-            response_id="resp_call_1",
-        ),
-        ChatResponse(messages=Message(role="assistant", text="It is sunny in Seattle."), response_id="resp_call_2"),
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    result = await agent.run("What's the weather in Seattle?", session=session)
-
-    provider_state = session.state[provider.source_id]
-    stored_messages = cast(list[Message], provider_state["messages"])
-
-    assert result.text == "It is sunny in Seattle."
-    assert result.response_id is None
-    assert chat_client_base.call_count == 2
-    assert provider_state["get_call_count"] == 2
-    assert provider_state["save_call_count"] == 2
-    assert stored_messages[-1].text == "It is sunny in Seattle."
-    assert session.service_session_id is None
-
-
-async def test_chat_agent_persists_history_per_service_call_streaming(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    session = AgentSession()
-    session.state[provider.source_id] = {
-        "messages": [
-            Message(role="user", text="Earlier question"),
-            Message(role="assistant", text="Earlier answer"),
-        ]
-    }
-    chat_client_base.streaming_responses = [
-        [
-            ChatResponseUpdate(
-                contents=[
-                    Content.from_function_call(
-                        call_id="call_1",
-                        name="lookup_weather",
-                        arguments='{"location": "Seattle"}',
-                    )
-                ],
-                role="assistant",
-                finish_reason="stop",
-                response_id="resp_call_1",
-            )
-        ],
-        [
-            ChatResponseUpdate(
-                contents=[Content.from_text("It is sunny in Seattle.")],
-                role="assistant",
-                finish_reason="stop",
-                response_id="resp_call_2",
-            )
-        ],
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    stream = agent.run("What's the weather in Seattle?", session=session, stream=True)
-    async for _ in stream:
-        pass
-    result = await stream.get_final_response()
-
-    provider_state = session.state[provider.source_id]
-    stored_messages = cast(list[Message], provider_state["messages"])
-
-    assert result.text == "It is sunny in Seattle."
-    assert result.response_id is None
-    assert chat_client_base.call_count == 2
-    assert provider_state["get_call_count"] == 2
-    assert provider_state["save_call_count"] == 2
-    assert stored_messages[-1].text == "It is sunny in Seattle."
-    assert session.service_session_id is None
-
-
-async def test_streaming_per_service_call_persistence_hides_response_id_from_after_run(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _ResponseIdRecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-    chat_client_base.streaming_responses = [
-        [
-            ChatResponseUpdate(
-                contents=[
-                    Content.from_function_call(
-                        call_id="call_1",
-                        name="lookup_weather",
-                        arguments='{"location": "Seattle"}',
-                    )
-                ],
-                role="assistant",
-                finish_reason="stop",
-                response_id="resp_call_1",
-            )
-        ],
-        [
-            ChatResponseUpdate(
-                contents=[Content.from_text("It is sunny in Seattle.")],
-                role="assistant",
-                finish_reason="stop",
-                response_id="resp_call_2",
-            )
-        ],
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    stream = agent.run("What's the weather in Seattle?", session=session, stream=True)
-    async for _ in stream:
-        pass
-    result = await stream.get_final_response()
-
-    provider_state = session.state[provider.source_id]
-
-    assert result.response_id is None
-    assert provider_state["response_ids"] == [None, None]
-
-
-async def test_per_service_call_persistence_uses_real_service_storage_when_client_stores_by_default(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    chat_client_base.STORES_BY_DEFAULT = True  # type: ignore[attr-defined]
-
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-    chat_client_base.run_responses = [
-        ChatResponse(
-            messages=Message(
-                role="assistant",
-                contents=[
-                    Content.from_function_call(
-                        call_id="call_1",
-                        name="lookup_weather",
-                        arguments='{"location": "Seattle"}',
-                    )
-                ],
-            ),
-            conversation_id="resp_service_managed",
-            response_id="resp_call_1",
-        ),
-        ChatResponse(
-            messages=Message(role="assistant", text="It is sunny in Seattle."),
-            conversation_id="resp_service_managed",
-            response_id="resp_call_2",
-        ),
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    result = await agent.run("What's the weather in Seattle?", session=session)
-
-    provider_state = session.state[provider.source_id]
-
-    assert result.text == "It is sunny in Seattle."
-    assert result.response_id == "resp_call_2"
-    assert chat_client_base.call_count == 2
-    assert "get_call_count" not in provider_state
-    assert "save_call_count" not in provider_state
-    assert session.service_session_id == "resp_service_managed"
-
-
-async def test_service_storage_updates_session_handle_per_service_call_before_non_streaming_failure(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    chat_client_base.STORES_BY_DEFAULT = True  # type: ignore[attr-defined]
-
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-    first_response = ChatResponse(
-        messages=Message(
-            role="assistant",
-            contents=[
-                Content.from_function_call(
-                    call_id="call_1",
-                    name="lookup_weather",
-                    arguments='{"location": "Seattle"}',
-                )
-            ],
-        ),
-        conversation_id="resp_call_1",
-        response_id="resp_call_1",
-    )
-    mock_get_non_streaming_response = AsyncMock(
-        side_effect=[first_response, RuntimeError("service down")],
-    )
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    with (
-        patch.object(chat_client_base, "_get_non_streaming_response", new=mock_get_non_streaming_response),
-        pytest.raises(RuntimeError, match="service down"),
-    ):
-        await agent.run("What's the weather in Seattle?", session=session)
-
-    assert mock_get_non_streaming_response.await_count == 2
-    assert session.service_session_id == "resp_call_1"
-
-
-async def test_service_storage_updates_session_handle_per_service_call_before_streaming_failure(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-
-    @tool(name="lookup_weather", approval_mode="never_require")
-    def lookup_weather(location: str) -> str:
-        return f"Weather in {location}: sunny"
-
-    chat_client_base.STORES_BY_DEFAULT = True  # type: ignore[attr-defined]
-
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-
-    async def _first_stream_updates() -> AsyncIterable[ChatResponseUpdate]:
-        yield ChatResponseUpdate(
-            contents=[
-                Content.from_function_call(
-                    call_id="call_1",
-                    name="lookup_weather",
-                    arguments='{"location": "Seattle"}',
-                )
-            ],
-            role="assistant",
-            finish_reason="stop",
-        )
-
-    def _finalize_first_stream(_updates: Sequence[ChatResponseUpdate]) -> ChatResponse[Any]:
-        return ChatResponse(
-            messages=Message(
-                role="assistant",
-                contents=[
-                    Content.from_function_call(
-                        call_id="call_1",
-                        name="lookup_weather",
-                        arguments='{"location": "Seattle"}',
-                    )
-                ],
-            ),
-            conversation_id="resp_call_1",
-            response_id="resp_call_1",
-        )
-
-    first_stream = ResponseStream(_first_stream_updates(), finalizer=_finalize_first_stream)
-    mock_get_streaming_response = MagicMock(side_effect=[first_stream, RuntimeError("service down")])
-
-    agent = Agent(
-        client=chat_client_base,
-        tools=[lookup_weather],
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    with (
-        patch.object(chat_client_base, "_get_streaming_response", new=mock_get_streaming_response),
-        pytest.raises(RuntimeError, match="service down"),
-    ):
-        stream = agent.run("What's the weather in Seattle?", session=session, stream=True)
-        async for _ in stream:
-            pass
-
-    assert mock_get_streaming_response.call_count == 2
-    assert session.service_session_id == "resp_call_1"
-
-
-async def test_chat_agent_without_per_service_call_persistence_preserves_response_id(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    chat_client_base.run_responses = [
-        ChatResponse(
-            messages=Message(role="assistant", text="Hello"),
-            response_id="resp_call_1",
-        )
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        context_providers=[InMemoryHistoryProvider()],
-    )
-
-    result = await agent.run("Hello", session=AgentSession(), options={"store": False})
-
-    assert result.response_id == "resp_call_1"
-
-
-async def test_per_service_call_persistence_rejects_real_service_conversation_id(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-    chat_client_base.STORES_BY_DEFAULT = True  # type: ignore[attr-defined]
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-    chat_client_base.run_responses = [
-        ChatResponse(
-            messages=Message(role="assistant", text="Hello"),
-            conversation_id="resp_service_managed",
-        )
-    ]
-
-    agent = Agent(
-        client=chat_client_base,
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    with pytest.raises(
-        ChatClientInvalidResponseException,
-        match="require_per_service_call_history_persistence cannot be used",
-    ):
-        await agent.run("Hello", session=session, options={"store": False})
-
-
-async def test_per_service_call_persistence_rejects_existing_conversation_id_when_service_not_storing_history(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    provider = _RecordingHistoryProvider()
-    session = AgentSession()
-    session.state[provider.source_id] = {"messages": []}
-
-    agent = Agent(
-        client=chat_client_base,
-        context_providers=[provider],
-        require_per_service_call_history_persistence=True,
-    )
-
-    with pytest.raises(
-        AgentInvalidRequestException,
-        match="require_per_service_call_history_persistence cannot be used",
-    ):
-        await agent.run("Hello", session=session, options={"store": False, "conversation_id": "existing_conversation"})
-
-
 async def test_chat_client_agent_run_with_session(chat_client_base: SupportsChatGetResponse) -> None:
     mock_response = ChatResponse(
         messages=[Message(role="assistant", contents=[Content.from_text("test response")])],
@@ -1043,7 +586,7 @@ async def test_chat_client_agent_author_name_is_used_from_response(
 
 
 # Mock context provider for testing
-class MockContextProvider(ContextProvider):
+class MockContextProvider(BaseContextProvider):
     def __init__(self, messages: list[Message] | None = None) -> None:
         super().__init__(source_id="mock")
         self.context_messages = messages
@@ -2180,7 +1723,7 @@ async def test_agent_create_session_with_context_providers(
 ):
     """Test that create_session works when context_providers are set on the agent."""
 
-    class TestContextProvider(ContextProvider):
+    class TestContextProvider(BaseContextProvider):
         def __init__(self):
             super().__init__(source_id="test")
 
@@ -2255,7 +1798,7 @@ async def test_chat_agent_context_provider_adds_tools_when_agent_has_none(
         """A tool provided by context."""
         return text
 
-    class ToolContextProvider(ContextProvider):
+    class ToolContextProvider(BaseContextProvider):
         def __init__(self):
             super().__init__(source_id="tool-context")
 
@@ -2284,7 +1827,7 @@ async def test_chat_agent_context_provider_adds_instructions_when_agent_has_none
 ):
     """Test that context provider instructions are used when agent has no default instructions."""
 
-    class InstructionContextProvider(ContextProvider):
+    class InstructionContextProvider(BaseContextProvider):
         def __init__(self):
             super().__init__(source_id="instruction-context")
 
@@ -2306,33 +1849,6 @@ async def test_chat_agent_context_provider_adds_instructions_when_agent_has_none
     assert options.get("instructions") == "Context-provided instructions"
 
 
-async def test_chat_agent_context_provider_adds_middleware_when_agent_has_none(
-    chat_client_base: SupportsChatGetResponse,
-) -> None:
-    """Test that context provider middleware is collected during preparation."""
-
-    @chat_middleware
-    async def context_chat_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-        await call_next()
-
-    class MiddlewareContextProvider(ContextProvider):
-        def __init__(self) -> None:
-            super().__init__(source_id="middleware-context")
-
-        async def before_run(self, *, agent, session, context, state) -> None:
-            context.extend_middleware("middleware-context", context_chat_middleware)
-
-    agent = Agent(client=chat_client_base, context_providers=[MiddlewareContextProvider()])
-
-    session_context, _ = await agent._prepare_session_and_messages(  # type: ignore[reportPrivateUsage]
-        session=None,
-        input_messages=[Message(role="user", text="Hello")],
-    )
-
-    assert session_context.middleware["middleware-context"] == [context_chat_middleware]
-    assert session_context.get_middleware() == [context_chat_middleware]
-
-
 # region STORES_BY_DEFAULT tests
 
 

python/packages/core/tests/core/test_middleware_with_agent.py

@@ -15,7 +15,6 @@ from agent_framework import (
     ChatResponse,
     ChatResponseUpdate,
     Content,
-    ContextProvider,
     FunctionInvocationContext,
     FunctionMiddleware,
     FunctionTool,
@@ -465,31 +464,6 @@ class TestChatAgentMultipleMiddlewareOrdering:
         expected_order = ["class_agent_before", "function_agent_before", "function_agent_after", "class_agent_after"]
         assert execution_order == expected_order
 
-    async def test_provider_added_agent_middleware_is_rejected(self, chat_client_base: "MockBaseChatClient") -> None:
-        """Test provider-added agent middleware is rejected explicitly."""
-
-        @agent_middleware
-        async def provider_middleware(context: AgentContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        class ProviderMiddlewareContextProvider(ContextProvider):
-            def __init__(self) -> None:
-                super().__init__(source_id="provider-middleware")
-
-            async def before_run(self, *, agent, session, context, state) -> None:
-                context.extend_middleware(self.source_id, provider_middleware)
-
-        agent = Agent(
-            client=chat_client_base,
-            context_providers=[ProviderMiddlewareContextProvider()],
-        )
-
-        with pytest.raises(
-            MiddlewareException,
-            match="Context providers may only add chat or function middleware",
-        ):
-            await agent.run([Message(role="user", text="test message")])
-
 
 # region Tool Functions for Testing
 
@@ -2092,121 +2066,6 @@ class TestChatAgentChatMiddleware:
             "agent_middleware_after",
         ]
 
-    async def test_provider_added_chat_and_function_middleware_are_forwarded(
-        self, chat_client_base: "MockBaseChatClient"
-    ) -> None:
-        """Test provider-added chat and function middleware forwarding and ordering."""
-        execution_order: list[str] = []
-
-        @chat_middleware
-        async def constructor_chat_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            execution_order.append("constructor_chat_before")
-            await call_next()
-            execution_order.append("constructor_chat_after")
-
-        @chat_middleware
-        async def provider_chat_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            execution_order.append("provider_chat_before")
-            await call_next()
-            execution_order.append("provider_chat_after")
-
-        @chat_middleware
-        async def run_chat_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            execution_order.append("run_chat_before")
-            await call_next()
-            execution_order.append("run_chat_after")
-
-        @function_middleware
-        async def constructor_function_middleware(
-            context: FunctionInvocationContext, call_next: Callable[[], Awaitable[None]]
-        ) -> None:
-            execution_order.append("constructor_function_before")
-            await call_next()
-            execution_order.append("constructor_function_after")
-
-        @function_middleware
-        async def provider_function_middleware(
-            context: FunctionInvocationContext, call_next: Callable[[], Awaitable[None]]
-        ) -> None:
-            execution_order.append("provider_function_before")
-            await call_next()
-            execution_order.append("provider_function_after")
-
-        @function_middleware
-        async def run_function_middleware(
-            context: FunctionInvocationContext, call_next: Callable[[], Awaitable[None]]
-        ) -> None:
-            execution_order.append("run_function_before")
-            await call_next()
-            execution_order.append("run_function_after")
-
-        class ProviderMiddlewareContextProvider(ContextProvider):
-            def __init__(self) -> None:
-                super().__init__(source_id="provider-middleware")
-
-            async def before_run(self, *, agent, session, context, state) -> None:
-                context.extend_middleware(
-                    self.source_id,
-                    [
-                        provider_chat_middleware,
-                        provider_function_middleware,
-                    ],
-                )
-
-        chat_client_base.run_responses = [
-            ChatResponse(
-                messages=[
-                    Message(
-                        role="assistant",
-                        contents=[
-                            Content.from_function_call(
-                                call_id="call_provider",
-                                name="sample_tool_function",
-                                arguments='{"location": "Seattle"}',
-                            )
-                        ],
-                    )
-                ]
-            ),
-            ChatResponse(messages=[Message(role="assistant", text="Final response")]),
-        ]
-
-        agent = Agent(
-            client=chat_client_base,
-            middleware=[constructor_chat_middleware, constructor_function_middleware],
-            context_providers=[ProviderMiddlewareContextProvider()],
-            tools=[sample_tool_function],
-        )
-
-        response = await agent.run(
-            [Message(role="user", text="Get weather for Seattle")],
-            middleware=[run_chat_middleware, run_function_middleware],
-        )
-
-        assert response is not None
-        assert chat_client_base.call_count == 2
-        assert response.messages[-1].text == "Final response"
-        assert execution_order == [
-            "constructor_chat_before",
-            "run_chat_before",
-            "provider_chat_before",
-            "provider_chat_after",
-            "run_chat_after",
-            "constructor_chat_after",
-            "constructor_function_before",
-            "run_function_before",
-            "provider_function_before",
-            "provider_function_after",
-            "run_function_after",
-            "constructor_function_after",
-            "constructor_chat_before",
-            "run_chat_before",
-            "provider_chat_before",
-            "provider_chat_after",
-            "run_chat_after",
-            "constructor_chat_after",
-        ]
-
     async def test_agent_middleware_can_access_and_override_options(self) -> None:
         """Test that agent middleware can access and override runtime options."""
         captured_options: dict[str, Any] = {}

python/packages/core/tests/core/test_sessions.py

@@ -1,26 +1,16 @@
 # Copyright (c) Microsoft. All rights reserved.
 
 import json
-from collections.abc import Awaitable, Callable, Sequence
+from collections.abc import Sequence
 
-import pytest
-
-from agent_framework import (
-    AgentContext,
+from agent_framework import Message
+from agent_framework._sessions import (
     AgentSession,
     BaseContextProvider,
     BaseHistoryProvider,
-    ChatContext,
-    ContextProvider,
-    HistoryProvider,
     InMemoryHistoryProvider,
-    Message,
     SessionContext,
-    agent_middleware,
-    chat_middleware,
 )
-from agent_framework._sessions import LOCAL_HISTORY_CONVERSATION_ID, is_local_history_conversation_id
-from agent_framework.exceptions import MiddlewareException
 
 # ---------------------------------------------------------------------------
 # SessionContext tests
@@ -112,50 +102,6 @@ class TestSessionContext:
         ctx.extend_instructions("sys", ["Be helpful", "Be concise"])
         assert ctx.instructions == ["Be helpful", "Be concise"]
 
-    def test_extend_middleware_creates_key_and_appends(self) -> None:
-        ctx = SessionContext(input_messages=[])
-
-        @chat_middleware
-        async def first_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        @chat_middleware
-        async def second_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        ctx.extend_middleware("rag", first_middleware)
-        ctx.extend_middleware("rag", [second_middleware])
-
-        assert ctx.middleware["rag"] == [first_middleware, second_middleware]
-        assert ctx.get_middleware() == [first_middleware, second_middleware]
-
-    def test_extend_middleware_preserves_source_order(self) -> None:
-        ctx = SessionContext(input_messages=[])
-
-        @chat_middleware
-        async def first_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        @chat_middleware
-        async def second_middleware(context: ChatContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        ctx.extend_middleware("a", first_middleware)
-        ctx.extend_middleware("b", second_middleware)
-
-        assert list(ctx.middleware.keys()) == ["a", "b"]
-        assert ctx.get_middleware() == [first_middleware, second_middleware]
-
-    def test_extend_middleware_rejects_agent_middleware(self) -> None:
-        ctx = SessionContext(input_messages=[])
-
-        @agent_middleware
-        async def provider_agent_middleware(context: AgentContext, call_next: Callable[[], Awaitable[None]]) -> None:
-            await call_next()
-
-        with pytest.raises(MiddlewareException, match="Context providers may only add chat or function middleware"):
-            ctx.extend_middleware("rag", provider_agent_middleware)
-
     def test_get_messages_all(self) -> None:
         ctx = SessionContext(input_messages=[])
         ctx.extend_messages("a", [Message(role="user", contents=["a"])])
@@ -208,58 +154,37 @@ class TestSessionContext:
         ctx._response = resp
         assert ctx.response is resp
 
-    def test_local_history_conversation_id_sentinel(self) -> None:
-        assert is_local_history_conversation_id(LOCAL_HISTORY_CONVERSATION_ID) is True
-        assert is_local_history_conversation_id("some_other_id") is False
-
 
 # ---------------------------------------------------------------------------
-# ContextProvider tests
+# BaseContextProvider tests
 # ---------------------------------------------------------------------------
 
 
-class TestContextProvider:
+class TestContextProviderBase:
     def test_source_id_required(self) -> None:
-        provider = ContextProvider(source_id="test")
+        provider = BaseContextProvider(source_id="test")
         assert provider.source_id == "test"
 
     async def test_before_run_is_noop(self) -> None:
-        provider = ContextProvider(source_id="test")
+        provider = BaseContextProvider(source_id="test")
         session = AgentSession()
         ctx = SessionContext(input_messages=[])
         # Should not raise
         await provider.before_run(agent=None, session=session, context=ctx, state={})  # type: ignore[arg-type]
 
     async def test_after_run_is_noop(self) -> None:
-        provider = ContextProvider(source_id="test")
+        provider = BaseContextProvider(source_id="test")
         session = AgentSession()
         ctx = SessionContext(input_messages=[])
         await provider.after_run(agent=None, session=session, context=ctx, state={})  # type: ignore[arg-type]
 
 
 # ---------------------------------------------------------------------------
-# Deprecated provider alias tests
+# BaseHistoryProvider tests
 # ---------------------------------------------------------------------------
 
 
-class TestDeprecatedProviderAliases:
-    def test_base_context_provider_warns_and_is_compatible(self) -> None:
-        with pytest.warns(DeprecationWarning, match="BaseContextProvider is deprecated. Use ContextProvider instead."):
-            provider = BaseContextProvider(source_id="test")
-
-        assert isinstance(provider, ContextProvider)
-
-    def test_base_provider_aliases_preserve_subtyping(self) -> None:
-        assert issubclass(BaseContextProvider, ContextProvider)
-        assert issubclass(BaseHistoryProvider, HistoryProvider)
-
-
-# ---------------------------------------------------------------------------
-# HistoryProvider tests
-# ---------------------------------------------------------------------------
-
-
-class ConcreteHistoryProvider(HistoryProvider):
+class ConcreteHistoryProvider(BaseHistoryProvider):
     """Concrete test implementation."""
 
     def __init__(self, source_id: str, stored_messages: list[Message] | None = None, **kwargs) -> None:

python/packages/core/tests/core/test_types.py

@@ -43,7 +43,7 @@ from agent_framework._types import (
     add_usage_details,
     validate_tool_mode,
 )
-from agent_framework.exceptions import AdditionItemMismatch, ContentError
+from agent_framework.exceptions import ContentError
 
 
 @fixture
@@ -1526,88 +1526,6 @@ def test_text_reasoning_content_iadd_coverage():
     assert t1.text == "Thinking 1 Thinking 2"
 
 
-def test_text_reasoning_content_add_preserves_id():
-    """Test that coalescing text_reasoning Content preserves the id field."""
-
-    t1 = Content.from_text_reasoning(id="rs_abc123", text="Thinking part 1")
-    t2 = Content.from_text_reasoning(id="rs_abc123", text=" part 2")
-
-    result = t1 + t2
-    assert result.text == "Thinking part 1 part 2"
-    assert result.id == "rs_abc123"
-
-
-def test_text_reasoning_content_add_id_fallback_to_other():
-    """Test that coalescing falls back to other's id when self has no id."""
-
-    t1 = Content.from_text_reasoning(text="Thinking part 1")
-    t2 = Content.from_text_reasoning(id="rs_abc123", text=" part 2")
-
-    result = t1 + t2
-    assert result.id == "rs_abc123"
-
-
-def test_text_reasoning_content_add_preserves_id_with_encrypted_content():
-    """Test that id and encrypted_content both survive coalescing for round-trip."""
-
-    t1 = Content.from_text_reasoning(
-        id="rs_abc123",
-        text="Thinking",
-        additional_properties={"encrypted_content": "enc_blob_data"},
-    )
-    t2 = Content.from_text_reasoning(id="rs_abc123", text=" more")
-
-    result = t1 + t2
-    assert result.text == "Thinking more"
-    assert result.id == "rs_abc123"
-    assert result.additional_properties.get("encrypted_content") == "enc_blob_data"
-
-
-def test_text_reasoning_content_add_conflicting_ids_raises():
-    """Test that coalescing text_reasoning Content with different ids raises AdditionItemMismatch."""
-
-    t1 = Content.from_text_reasoning(id="rs_abc123", text="Thinking part 1")
-    t2 = Content.from_text_reasoning(id="rs_xyz789", text=" part 2")
-
-    with pytest.raises(AdditionItemMismatch, match="different ids"):
-        t1 + t2
-
-
-def test_text_reasoning_content_add_neither_has_id():
-    """Test that coalescing text_reasoning Content when neither has an id results in None id."""
-
-    t1 = Content.from_text_reasoning(text="Thinking part 1")
-    t2 = Content.from_text_reasoning(text=" part 2")
-
-    result = t1 + t2
-    assert result.text == "Thinking part 1 part 2"
-    assert result.id is None
-
-
-def test_coalesce_text_reasoning_with_different_ids():
-    """Test that _coalesce_text_content keeps separate text_reasoning items when IDs differ.
-
-    Regression test: streaming responses can produce multiple text_reasoning
-    segments with distinct IDs. These must not be merged into one.
-    """
-    from agent_framework._types import _coalesce_text_content
-
-    contents = [
-        Content.from_text_reasoning(id="rs_aaa", text="Thinking A1"),
-        Content.from_text_reasoning(id="rs_aaa", text=" A2"),
-        Content.from_text_reasoning(id="rs_bbb", text="Thinking B1"),
-        Content.from_text_reasoning(id="rs_bbb", text=" B2"),
-    ]
-
-    _coalesce_text_content(contents, "text_reasoning")
-
-    assert len(contents) == 2
-    assert contents[0].id == "rs_aaa"
-    assert contents[0].text == "Thinking A1 A2"
-    assert contents[1].id == "rs_bbb"
-    assert contents[1].text == "Thinking B1 B2"
-
-
 def test_comprehensive_to_dict_exclude_options():
     """Test to_dict methods with various exclude options for better coverage."""
 

python/packages/foundry/agent_framework_foundry/_agent.py

@@ -17,9 +17,9 @@ from typing import TYPE_CHECKING, Any, ClassVar, Generic, cast
 from agent_framework import (
     AGENT_FRAMEWORK_USER_AGENT,
     AgentMiddlewareLayer,
+    BaseContextProvider,
     ChatAndFunctionMiddlewareTypes,
     ChatMiddlewareLayer,
-    ContextProvider,
     FunctionInvocationConfiguration,
     FunctionInvocationLayer,
     FunctionTool,
@@ -50,8 +50,8 @@ else:
 if TYPE_CHECKING:
     from agent_framework import (
         Agent,
+        BaseContextProvider,
         ChatAndFunctionMiddlewareTypes,
-        ContextProvider,
         MiddlewareTypes,
         ToolTypes,
     )
@@ -224,9 +224,8 @@ class RawFoundryAgentChatClient(  # type: ignore[misc]
         instructions: str | None = None,
         tools: ToolTypes | Callable[..., Any] | Sequence[ToolTypes | Callable[..., Any]] | None = None,
         default_options: FoundryAgentOptionsT | Mapping[str, Any] | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         function_invocation_configuration: FunctionInvocationConfiguration | None = None,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
@@ -247,7 +246,6 @@ class RawFoundryAgentChatClient(  # type: ignore[misc]
                 tools=function_tools,
                 context_providers=context_providers,
                 middleware=middleware,
-                require_per_service_call_history_persistence=require_per_service_call_history_persistence,
                 client_type=cast(type[RawFoundryAgentChatClient], self.__class__),
                 id=id,
                 name=self.agent_name if name is None else name,
@@ -470,7 +468,7 @@ class RawFoundryAgent(  # type: ignore[misc]
         project_client: AIProjectClient | None = None,
         allow_preview: bool | None = None,
         tools: FunctionTool | Callable[..., Any] | Sequence[FunctionTool | Callable[..., Any]] | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
         client_type: type[RawFoundryAgentChatClient] | None = None,
         env_file_path: str | None = None,
@@ -480,7 +478,6 @@ class RawFoundryAgent(  # type: ignore[misc]
         description: str | None = None,
         instructions: str | None = None,
         default_options: FoundryAgentOptionsT | Mapping[str, Any] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         function_invocation_configuration: FunctionInvocationConfiguration | None = None,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
@@ -510,8 +507,6 @@ class RawFoundryAgent(  # type: ignore[misc]
             description: Optional local description for the local agent wrapper.
             instructions: Optional instructions for the local agent wrapper.
             default_options: Default chat options for the local agent wrapper.
-            require_per_service_call_history_persistence: Whether to require per-service-call
-                chat history persistence when using local history providers.
             function_invocation_configuration: Optional function invocation configuration override.
             compaction_strategy: Optional agent-level in-run compaction override.
             tokenizer: Optional agent-level tokenizer override.
@@ -553,7 +548,6 @@ class RawFoundryAgent(  # type: ignore[misc]
             default_options=cast(FoundryAgentOptionsT | None, default_options),
             context_providers=context_providers,
             middleware=middleware,
-            require_per_service_call_history_persistence=require_per_service_call_history_persistence,
             compaction_strategy=compaction_strategy,
             tokenizer=tokenizer,
             additional_properties=dict(additional_properties) if additional_properties is not None else None,
@@ -667,7 +661,7 @@ class FoundryAgent(  # type: ignore[misc]
         project_client: AIProjectClient | None = None,
         allow_preview: bool | None = None,
         tools: FunctionTool | Callable[..., Any] | Sequence[FunctionTool | Callable[..., Any]] | None = None,
-        context_providers: Sequence[ContextProvider] | None = None,
+        context_providers: Sequence[BaseContextProvider] | None = None,
         middleware: Sequence[MiddlewareTypes] | None = None,
         client_type: type[RawFoundryAgentChatClient] | None = None,
         env_file_path: str | None = None,
@@ -677,7 +671,6 @@ class FoundryAgent(  # type: ignore[misc]
         description: str | None = None,
         instructions: str | None = None,
         default_options: FoundryAgentOptionsT | Mapping[str, Any] | None = None,
-        require_per_service_call_history_persistence: bool = False,
         function_invocation_configuration: FunctionInvocationConfiguration | None = None,
         compaction_strategy: CompactionStrategy | None = None,
         tokenizer: TokenizerProtocol | None = None,
@@ -703,8 +696,6 @@ class FoundryAgent(  # type: ignore[misc]
             description: Optional local description for the local agent wrapper.
             instructions: Optional instructions for the local agent wrapper.
             default_options: Default chat options for the local agent wrapper.
-            require_per_service_call_history_persistence: Whether to require per-service-call
-                chat history persistence when using local history providers.
             function_invocation_configuration: Optional function invocation configuration override.
             compaction_strategy: Optional agent-level in-run compaction override.
             tokenizer: Optional agent-level tokenizer override.
@@ -728,7 +719,6 @@ class FoundryAgent(  # type: ignore[misc]
             description=description,
             instructions=instructions,
             default_options=default_options,
-            require_per_service_call_history_persistence=require_per_service_call_history_persistence,
             function_invocation_configuration=function_invocation_configuration,
             compaction_strategy=compaction_strategy,
             tokenizer=tokenizer,

python/packages/foundry/agent_framework_foundry/_memory_provider.py

@@ -1,9 +1,9 @@
 # Copyright (c) Microsoft. All rights reserved.
 
-"""Foundry Memory Context Provider using ContextProvider.
+"""Foundry Memory Context Provider using BaseContextProvider.
 
 This module provides ``FoundryMemoryProvider``, built on
-:class:`ContextProvider`.
+:class:`BaseContextProvider`.
 """
 
 from __future__ import annotations
@@ -16,7 +16,7 @@ from typing import TYPE_CHECKING, Any, ClassVar
 from agent_framework import (
     AGENT_FRAMEWORK_USER_AGENT,
     AgentSession,
-    ContextProvider,
+    BaseContextProvider,
     Message,
     SessionContext,
     load_settings,
@@ -46,8 +46,8 @@ class FoundryProjectSettings(TypedDict, total=False):
     project_endpoint: str | None
 
 
-class FoundryMemoryProvider(ContextProvider):
-    """Foundry Memory context provider using the new ContextProvider hooks pattern.
+class FoundryMemoryProvider(BaseContextProvider):
+    """Foundry Memory context provider using the new BaseContextProvider hooks pattern.
 
     Integrates Azure AI Foundry Memory Store for persistent semantic memory,
     searching and storing memories via the Azure AI Projects SDK.