Merge branch 'main' into copilot/5350-implement-repro-unit-test

Agent-Logs-Url: https://github.com/microsoft/agent-framework/sessions/e7100d8a-ca6d-48e6-8210-78ba33dbd53c

Co-authored-by: lokitoth <6936551+lokitoth@users.noreply.github.com>

.github/actions/python-setup/action.yml

@@ -32,13 +32,7 @@ runs:
               if grep -q "name = \"$pkg\"" "$f"; then
                 pkg_dir=$(dirname "$f" | sed 's|python/||')
                 echo "Excluding workspace package: $pkg ($pkg_dir)"
-                if awk '/^\[tool\.uv\.workspace\]/{f=1;next} /^\[/{f=0} f && /^exclude = \[/{found=1} END{exit !found}' python/pyproject.toml; then
-                  if ! awk '/^\[tool\.uv\.workspace\]/{f=1;next} /^\[/{f=0} f && /^exclude = \[/ && index($0, "\"'"$pkg_dir"'\"")' python/pyproject.toml | grep -q .; then
-                    sed -i.bak '/\[tool\.uv\.workspace\]/,/^\[/ { /^exclude = \[/ s|\]|, "'"$pkg_dir"'"]| }' python/pyproject.toml
-                  fi
-                else
-                  sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
-                fi
+                sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
                 sed -i.bak '/'"$pkg"' = { workspace = true }/d' python/pyproject.toml
               fi
             done
@@ -46,4 +40,4 @@ runs:
       - name: Install the project
         shell: bash
         run: |
-          cd python && uv sync --all-packages --all-extras --dev --prerelease=if-necessary-or-explicit
+          cd python && uv sync --all-packages --all-extras --dev -U --prerelease=if-necessary-or-explicit

docs/working/issue-5350-root-cause-validation-plan.md

@@ -0,0 +1,173 @@
+# Issue #5350 — Root-cause validation plan
+
+**Issue:** [`.NET: [Bug]: Checkpoint round-trip loses ToolApprovalRequestContent.ToolCall concrete type (FunctionCallContent → base ToolCallContent), breaking FICC approval resume`](https://github.com/microsoft/agent-framework/issues/5350)
+
+**Status of repro:** A focused repro test class
+`dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/ToolApprovalRequestCheckpointReproTests.cs`
+was added covering seven progressively more end-to-end variants of the path the issue
+describes — including a **maximal** end-to-end test that uses a real
+`ChatClientAgent` driven by `FunctionInvokingChatClient` with an
+`ApprovalRequiredAIFunction`. **All seven tests pass** on `main`, consistently across
+5 back-to-back runs, i.e. *the bug as described does not reproduce* at any of the
+layers exercised here:
+
+| # | Test                                                                                | What it exercises                                                                                                                                                  | Result |
+|---|-------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------|
+| 1 | `Repro_5350_ToolApprovalRequestContent_DirectJsonMarshallerRoundtrip_PreservesFunctionCallContent` | `JsonMarshaller.Marshal/Marshal<T>` on `ToolApprovalRequestContent` directly (same options chain as `CheckpointManager.CreateJson`)                                | Pass   |
+| 2 | `Repro_5350_ToolApprovalRequestContent_WrappedInPortableValue_PreservesFunctionCallContent`       | Same, wrapped in a `PortableValue` (as `PortableMessageEnvelope` would store it)                                                                                  | Pass   |
+| 3 | `Repro_5350_ToolApprovalRequestContent_AsExternalRequestData_PreservesFunctionCallContent`        | Same, as the `Data` payload of an `ExternalRequest`                                                                                                                | Pass   |
+| 4 | `Repro_5350_DirectJsonMarshallerRoundtrip_IsDeterministic`                          | 25× repetition of #1 to rule out flakiness / JIT order                                                                                                             | Pass   |
+| 5 | `Repro_5350_CaptureWireFormat_ForInspection`                                        | Captures the on-the-wire shape so we can compare against the OP's SQL row                                                                                          | Pass   |
+| 6 | `Repro_5350_EndToEnd_JsonCheckpointResume_PreservesFunctionCallContentAsync`        | Full `CheckpointManager.CreateJson(InMemoryJsonStore) → RunStreamingAsync → SuperStep checkpoint → ResumeStreamingAsync` cycle with a `RequestPort<TARC, TARR>`    | Pass   |
+| 7 | `Repro_5350_EndToEnd_ChatClientAgent_WithApprovalRequiredTool_JsonCheckpointResume_PreservesFunctionCallContentAndInvokesToolAsync` | **Maximal**: `ChatClientAgent` over a `MockChatClient` with an `ApprovalRequiredAIFunction`, single-agent `WorkflowBuilder` (no orchestration), `CheckpointManager.CreateJson(InMemoryJsonStore)`. Asserts both that the resumed `RequestInfoEvent.Request` still carries a `FunctionCallContent` AND that approving the request actually invokes the underlying `AIFunction` and lets the workflow continue. | Pass   |
+
+This is **consistent with [@lokitoth's second comment](https://github.com/microsoft/agent-framework/issues/5350#issuecomment-4379664401)**:
+
+> Looking at the MEAI types, it does have `[JsonDerivedType(typeof(FunctionCallContent), "functionCall")]` set on it, and has had it that way for some time, so it is unlikely to be the root cause. […] `JsonMarshaller` […] takes an optional `JsonSerializationOptions` provided by the user […] but this is used only if the internal one (via `WorkflowsJsonUtilities`, which chains to `AgentAbstractionsJsonUtilities`, which then chains to the `AIJsonUtilities` class) [is missing the type].
+
+Inspection of the actual wire format produced by `JsonMarshaller` for a
+`ToolApprovalRequestContent` containing a `FunctionCallContent` confirms the
+discriminator is emitted:
+
+```jsonc
+// TARC at top level
+{
+  "toolCall": {
+    "$type": "functionCall",      // ← polymorphism discriminator present
+    "name": "DoTheThing",
+    "arguments": { "x": 42 },
+    "informationalOnly": false,
+    "callId": "call-1"
+  },
+  "requestId": "req-1"
+}
+
+// TARC inside a PortableValue (= shape stored by PortableMessageEnvelope)
+{
+  "typeId": {
+    "assemblyName": "Microsoft.Extensions.AI.Abstractions, Version=10.5.0.0, …",
+    "typeName": "Microsoft.Extensions.AI.ToolApprovalRequestContent"
+  },
+  "value": {
+    "toolCall": {
+      "$type": "functionCall",
+      …
+    },
+    "requestId": "req-1"
+  }
+}
+```
+
+So the OP's stated root-cause hypothesis — *"`AIContent`/`ToolCallContent`/
+`FunctionCallContent` are missing `[JsonPolymorphic]`/`[JsonDerivedType]`, or
+`CheckpointManager.CreateJson` does not pull from `AIJsonUtilities.DefaultOptions`"*
+— is **not** what is producing the failure described in the issue. The annotations
+exist, the resolver chain wires them through, and the discriminator does survive
+both the direct `JsonMarshaller` round-trip and a real `Run → checkpoint → Resume`
+cycle for a `RequestPort` whose request type is `ToolApprovalRequestContent`.
+
+The remaining sections lay out, in priority order, the work needed to identify
+the *actual* root cause. The plan deliberately keeps the failing repro from
+above as the baseline ("this is what works") and walks outward from it toward
+the OP's reported scenario, varying one dimension at a time.
+
+## Plan
+
+### Track A — Reproduce in a configuration closer to the OP's pattern "B"
+
+The OP's repro path differs from the new tests in three concrete ways. Tests #7
+(maximal repro) and #8–#10 (A2 / A3 / A4 below) close all four gaps. The OP's
+specific hypothesis (`TARC.ToolCall is not FunctionCallContent` after resume) does
+not reproduce in any of them; A2 did however uncover a *separate, unrelated* bug.
+
+| Step | Variable that changes vs. the passing tests in this repo                                                                                              | Why it matters                                                                                                                                                                                                       | Outcome                                                                |
+|------|--------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------|
+| A1   | ~~Use `ChatClientAgent` + `ApprovalRequiredAIFunction` bound into a `WorkflowBuilder`~~ — **covered by test #7 in this PR; passes.**                  | Was the largest gap to the OP's repro. Closed.                                                                                                                                                                       | OP hypothesis disproved — `TARC.ToolCall is FunctionCallContent` post-resume, and the tool is actually invoked exactly once when the approval response is sent. |
+| A2   | Multi-agent variant: same as #7 but with the agent inside a `GroupChatBuilder` (the OP's actual orchestration) with `RoundRobinGroupChatManager`.     | If group chat re-encodes TARC as part of `ChatMessage.Contents` (`AIContent` polymorphism is two-deep through `ToolApprovalRequestContent`), one branch may resolve and the other not.                              | OP hypothesis disproved — `TARC.ToolCall is FunctionCallContent` post-resume. **But:** sending the approval response surfaces a *different* real bug — `FunctionInvokingChatClient.ExtractAndRemoveApprovalRequestsAndResponses` throws `ArgumentException: An item with the same key has already been added. Key: ficc_call-1`. Pinned by test as documented misbehavior. |
+| A2b  | Same as A2 but using `HandoffWorkflowBuilder` (initial agent has the approval tool, a no-op peer agent makes the handoff graph valid; the mock chat client never emits a `handoff_to_*` call). | If the duplicate-key bug from A2 is broader than `RoundRobinGroupChatManager` and lives in the shared `AIAgentHostExecutor` / `ChatProtocolExecutor` path, the handoff workflow should hit it too. | OP hypothesis disproved — `TARC.ToolCall is FunctionCallContent` post-resume **and** the workflow completes cleanly: tool invoked exactly once, zero errors, zero executor failures. The duplicate-key bug from A2 does **not** occur on the handoff path, narrowing it to the group-chat-specific orchestration. |
+| A3   | Same as #7 but with the checkpoint `JsonElement` round-tripped through `string` + `JsonDocument.Parse` between commit and retrieve (`StringRoundTripJsonStore`), emulating the SQL `nvarchar` hop in the OP's Dapper store.                                                                                | The OP uses Dapper + SQL Server. If the column / driver round-trip preserves ordering, this should be identity-preserving — but if it reorders metadata properties, the `$type` discriminator can be moved out of first position, which then requires `AllowOutOfOrderMetadataProperties = true`. | OP hypothesis disproved — byte-preserving string round-trip is identity-preserving for the relevant payload; `TARC.ToolCall is FunctionCallContent` post-resume; tool invoked exactly once. The OP's storage layer would have to *perturb* the JSON (e.g. reorder metadata) for this to reproduce. |
+| A4   | Same as #7 but with non-default `JsonSerializerOptions` (`JsonSerializerDefaults.Web`, no AIJsonUtilities resolver) passed as `customOptions` to `CheckpointManager.CreateJson`.                                                                                                                          | `JsonMarshaller.LookupTypeInfo` only goes to the external options when the internal chain doesn't know about the type. For most cases this won't trigger, but it's worth confirming that supplying a custom `JsonSerializerOptions` does not silently displace the internal chain.                            | OP hypothesis disproved — custom external options that DO NOT know about `AIContent` types are correctly ignored for known types; the internal `WorkflowsJsonUtilities.DefaultOptions` chain wins. `TARC.ToolCall is FunctionCallContent` post-resume; tool invoked exactly once. |
+
+### Track B — Validate the wire format the OP actually persists
+
+Once Track A has reproduced (or has clearly failed to reproduce) the symptom,
+ask the OP for one of the following, in order of preference:
+
+1. The raw `JsonElement.GetRawText()` they pass to their SQL store on commit,
+   and the raw string they read back on `RetrieveCheckpointAsync` — for the
+   exact checkpoint that contains the failing `ToolApprovalRequestContent`.
+   This tells us in a single round-trip whether:
+   - the `$type` discriminator is present on commit (rules out write-side bug),
+   - the `$type` discriminator survives the SQL round-trip (rules out store bug),
+   - the discriminator is in metadata-first position (rules out the
+     `AllowOutOfOrderMetadataProperties` story).
+2. A repro PR/gist that runs against `CheckpointManager.CreateJson(...)` with
+   an in-memory `JsonCheckpointStore` shim that mirrors how their SQL subclass
+   passes bytes through. The OP already offered this in the issue body
+   (*"I can produce a minimal standalone repro against a fake `IChatClient` if useful — let me know."*) — taking them up on it short-circuits a lot of guessing.
+
+### Track C — Defense-in-depth fixes worth landing regardless of root cause
+
+These are addressed in the OP's "Asks" section (asks 2–4) and are useful
+documentation/ergonomics improvements even if the root cause turns out to be in
+the OP's store implementation:
+
+1. **Doc-only**: in the XML docs for `CheckpointManager.CreateJson` and on the
+   `JsonCheckpointStore` base class, explicitly state that the internal options
+   chain through `WorkflowsJsonUtilities → AgentAbstractionsJsonUtilities →
+   AIJsonUtilities`, and that user-supplied `customOptions` are consulted only
+   when the internal chain has no `TypeInfo` for a requested type.
+2. **Doc-only**: document the contract that any user `JsonCheckpointStore`
+   subclass MUST preserve the exact byte sequence of the `JsonElement` it is
+   given. If the underlying store reorders JSON metadata, the consumer must opt
+   in by setting `AllowOutOfOrderMetadataProperties = true` on a
+   `JsonSerializerOptions` passed as `customOptions` to
+   `CheckpointManager.CreateJson(...)`.
+3. **Optional, only if Track A reproduces**: add a regression test mirroring
+   the failing path under `dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests`
+   so the fix is locked in.
+
+### Track D — Reject the OP's hypothesis (if not already done)
+
+The combination of:
+
+- the polymorphism annotations existing in `Microsoft.Extensions.AI` for some time
+  (per @lokitoth),
+- the resolver chain in `WorkflowsJsonUtilities.CreateDefaultOptions()` already
+  putting `AgentAbstractionsJsonUtilities.DefaultOptions.TypeInfoResolver` first
+  (which itself puts `AIJsonUtilities.DefaultOptions.TypeInfoResolver` first),
+- the wire format captured above showing `"$type": "functionCall"` is present,
+- the full `Run → checkpoint → Resume` test in this PR passing for a plain
+  `RequestPort<TARC, ToolApprovalResponseContent>` workflow, **and**
+- the maximal `ChatClientAgent` + `FunctionInvokingChatClient` +
+  `ApprovalRequiredAIFunction` test in this PR also passing — including the
+  assertion that the wrapped `AIFunction` is actually invoked exactly once after
+  approval and that the workflow then receives the resulting
+  `FunctionResultContent` and produces a final assistant message,
+
+is sufficient to **disprove** the OP's stated hypothesis. Once Track A or
+Track B identifies the actual cause, the issue should be updated with a brief
+explanation of why the original guess was incorrect, so future readers don't
+re-tread it.
+
+## Pointers for the next investigator
+
+- Repro tests:
+  `dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/ToolApprovalRequestCheckpointReproTests.cs`
+- Marshaller under test:
+  `dotnet/src/Microsoft.Agents.AI.Workflows/Checkpointing/JsonMarshaller.cs`
+- Where `CheckpointManager.CreateJson` enters that path:
+  `dotnet/src/Microsoft.Agents.AI.Workflows/CheckpointManager.cs`
+- Options chain (TARC ⇒ resolver):
+  `dotnet/src/Microsoft.Agents.AI.Workflows/WorkflowsJsonUtilities.cs`
+  → `dotnet/src/Microsoft.Agents.AI.Abstractions/AgentAbstractionsJsonUtilities.cs`
+  → `Microsoft.Extensions.AI.AIJsonUtilities.DefaultOptions`
+- `PortableValue`-side serialization (this is where `value.Value.GetType()` is
+  used on write, which is the most plausible *internal* place a polymorphism
+  bug could hide, but the wire capture above shows it is not the cause in the
+  TARC-as-RequestPort scenario):
+  `dotnet/src/Microsoft.Agents.AI.Workflows/Checkpointing/PortableValueConverter.cs`
+- Likely next code to inspect for Track A1/A2 (agent-host serialization path):
+  `dotnet/src/Microsoft.Agents.AI.Workflows/AIAgentHostExecutor*.cs` and
+  whatever turns the FICC-generated TARC into something
+  `AIAgentHostExecutor` stores in its state bag.

dotnet/Directory.Packages.props

@@ -112,7 +112,6 @@
     <PackageVersion Include="ModelContextProtocol" Version="1.1.0" />
     <!-- Hyperlight -->
     <PackageVersion Include="Hyperlight.HyperlightSandbox.Api" Version="0.4.0" />
-    <PackageVersion Include="Hyperlight.HyperlightSandbox.Guest.Python" Version="0.4.0" />
     <!-- Inference SDKs -->
     <PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
     <PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />

dotnet/agent-framework-dotnet.slnx

@@ -124,7 +124,6 @@
     <Project Path="samples/02-agents/Harness/Harness_Step01_Research/Harness_Step01_Research.csproj" />
     <Project Path="samples/02-agents/Harness/Harness_Step02_Research_WithBackgroundAgents/Harness_Step02_Research_WithBackgroundAgents.csproj" />
     <Project Path="samples/02-agents/Harness/Harness_Step03_DataProcessing/Harness_Step03_DataProcessing.csproj" />
-    <Project Path="samples/02-agents/Harness/Harness_Step04_CodeExecution/Harness_Step04_CodeExecution.csproj" />
     <Project Path="samples/02-agents/Harness/ConsoleReactiveFramework/ConsoleReactiveFramework.csproj" />
     <Project Path="samples/02-agents/Harness/ConsoleReactiveComponents/ConsoleReactiveComponents.csproj" />
   </Folder>

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/AnsiEscapes.cs

@@ -24,11 +24,6 @@ public static class AnsiEscapes
     /// </summary>
     public static string MoveCursor(int row, int column) => $"\x1b[{row};{column}H";
 
-    /// <summary>
-    /// Erases the current line from the cursor position to the end of the line (EL 0).
-    /// </summary>
-    public static string EraseToEndOfLine => "\x1b[0K";
-
     /// <summary>
     /// Erases the entire current line (EL 2).
     /// </summary>

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/ListSelection.cs

@@ -39,7 +39,7 @@ public class ListSelection : ConsoleReactiveComponent<ListSelectionProps, Consol
         {
             foreach (string line in props.Title.Split('\n'))
             {
-                Console.Write(AnsiEscapes.MoveCursor(props.Y + row, props.X));
+                Console.Write(AnsiEscapes.MoveCursor(this.Y + row, this.X));
                 Console.Write(AnsiEscapes.EraseEntireLine);
                 Console.Write(line);
                 row++;
@@ -51,7 +51,7 @@ public class ListSelection : ConsoleReactiveComponent<ListSelectionProps, Consol
 
         for (int i = 0; i < totalItems; i++)
         {
-            Console.Write(AnsiEscapes.MoveCursor(props.Y + row, props.X));
+            Console.Write(AnsiEscapes.MoveCursor(this.Y + row, this.X));
             Console.Write(AnsiEscapes.EraseEntireLine);
 
             bool isSelected = i == props.SelectedIndex;

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/TextInput.cs

@@ -58,11 +58,11 @@ public class TextInput : ConsoleReactiveComponent<TextInputProps, ConsoleReactiv
     public override void RenderCore(TextInputProps props, ConsoleReactiveState state)
     {
         int promptLength = props.Prompt.Length;
-        int textWidth = props.Width - promptLength;
+        int textWidth = this.Width - promptLength;
         string indent = new(' ', promptLength);
 
         // First line: prompt + start of text
-        Console.Write(AnsiEscapes.MoveCursor(props.Y, props.X));
+        Console.Write(AnsiEscapes.MoveCursor(this.Y, this.X));
         Console.Write(AnsiEscapes.EraseEntireLine);
         Console.Write(props.Prompt);
 
@@ -90,7 +90,7 @@ public class TextInput : ConsoleReactiveComponent<TextInputProps, ConsoleReactiv
         while (offset < props.Text.Length)
         {
             int chunk = Math.Min(textWidth, props.Text.Length - offset);
-            Console.Write(AnsiEscapes.MoveCursor(props.Y + row, props.X));
+            Console.Write(AnsiEscapes.MoveCursor(this.Y + row, this.X));
             Console.Write(AnsiEscapes.EraseEntireLine);
             Console.Write(indent);
             Console.Write(props.Text[offset..(offset + chunk)]);

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/TextPanel.cs

@@ -17,7 +17,7 @@ public record TextPanelProps : ConsoleReactiveProps
 /// <summary>
 /// A component that renders a list of pre-rendered string items vertically.
 /// Designed for rendering dynamic items in a non-scroll region that may be
-/// re-rendered on each update. If the component's <see cref="ConsoleReactiveProps.Height"/>
+/// re-rendered on each update. If the component's <see cref="ConsoleReactiveComponent.Height"/>
 /// exceeds the number of output lines, leftover lines are erased.
 /// </summary>
 public class TextPanel : ConsoleReactiveComponent<TextPanelProps, ConsoleReactiveState>
@@ -51,18 +51,18 @@ public class TextPanel : ConsoleReactiveComponent<TextPanelProps, ConsoleReactiv
 
             for (int j = 0; j < lineCount; j++)
             {
-                Console.Write(AnsiEscapes.MoveAndEraseLine(props.Y + currentRow));
+                Console.Write(AnsiEscapes.MoveAndEraseLine(this.Y + currentRow));
                 Console.Write(lines[j]);
                 currentRow++;
             }
         }
 
         // If the component height exceeds the output, erase leftover lines
-        if (props.Height > currentRow)
+        if (this.Height > currentRow)
         {
-            for (int i = currentRow; i < props.Height; i++)
+            for (int i = currentRow; i < this.Height; i++)
             {
-                Console.Write(AnsiEscapes.MoveAndEraseLine(props.Y + i));
+                Console.Write(AnsiEscapes.MoveAndEraseLine(this.Y + i));
             }
         }
     }

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/TextScrollPanel.cs

@@ -52,7 +52,7 @@ public class TextScrollPanel : ConsoleReactiveComponent<TextScrollPanelProps, Te
         }
 
         // Move cursor to the bottom of the scroll area
-        Console.Write(AnsiEscapes.MoveCursor(props.Y + props.Height - 1, props.X));
+        Console.Write(AnsiEscapes.MoveCursor(this.Y + this.Height - 1, this.X));
 
         // Output only new items since last rendered
         for (int i = state.RenderedCount; i < props.Items.Count; i++)

dotnet/samples/02-agents/Harness/ConsoleReactiveComponents/TopBottomRule.cs

@@ -9,6 +9,9 @@ namespace Harness.ConsoleReactiveComponents;
 /// </summary>
 public record TopBottomRuleProps : ConsoleReactiveProps
 {
+    /// <summary>Gets the width of the horizontal rules in characters.</summary>
+    public int Width { get; init; }
+
     /// <summary>Gets the foreground color of the horizontal rules. If <c>null</c>, the default terminal color is used.</summary>
     public ConsoleColor? Color { get; init; }
 }
@@ -29,7 +32,7 @@ public class TopBottomRule : ConsoleReactiveComponent<TopBottomRuleProps, Consol
         int childrenHeight = 0;
         foreach (var child in props.Children)
         {
-            childrenHeight += child.BaseProps?.Height ?? 0;
+            childrenHeight += child.Height;
         }
 
         // Top rule + children + bottom rule
@@ -48,11 +51,11 @@ public class TopBottomRule : ConsoleReactiveComponent<TopBottomRuleProps, Consol
         }
 
         // Top rule
-        Console.Write(AnsiEscapes.MoveCursor(props.Y, props.X));
+        Console.Write(AnsiEscapes.MoveCursor(this.Y, this.X));
         Console.Write(rule);
 
         // Render children stacked below the top rule
-        int currentY = props.Y + 1;
+        int currentY = this.Y + 1;
 
         if (props.Color.HasValue)
         {
@@ -61,9 +64,10 @@ public class TopBottomRule : ConsoleReactiveComponent<TopBottomRuleProps, Consol
 
         foreach (var child in props.Children)
         {
-            child.BaseProps = child.BaseProps! with { X = props.X, Y = currentY };
+            child.X = this.X;
+            child.Y = currentY;
             child.Render();
-            currentY += child.BaseProps.Height;
+            currentY += child.Height;
         }
 
         if (props.Color.HasValue)
@@ -72,7 +76,7 @@ public class TopBottomRule : ConsoleReactiveComponent<TopBottomRuleProps, Consol
         }
 
         // Bottom rule
-        Console.Write(AnsiEscapes.MoveCursor(currentY, props.X));
+        Console.Write(AnsiEscapes.MoveCursor(currentY, this.X));
         Console.Write(rule);
 
         if (props.Color.HasValue)

dotnet/samples/02-agents/Harness/ConsoleReactiveFramework/ConsoleReactiveComponent.cs

@@ -3,8 +3,8 @@
 namespace Harness.ConsoleReactiveFramework;
 
 /// <summary>
-/// Abstract base class for all console UI components. Provides access to layout
-/// through <see cref="BaseProps"/> and a <see cref="Render"/> method for drawing to the console.
+/// Abstract base class for all console UI components. Provides layout properties
+/// (position and size) and a <see cref="Render"/> method for drawing to the console.
 /// Derive from <see cref="ConsoleReactiveComponent{TProps, TState}"/> instead of this class directly.
 /// </summary>
 public abstract class ConsoleReactiveComponent
@@ -13,21 +13,20 @@ public abstract class ConsoleReactiveComponent
     {
     }
 
-    /// <summary>
-    /// Gets or sets the component's props as the base <see cref="ConsoleReactiveProps"/> type.
-    /// Used by parent components to set layout (X, Y, Width, Height) on children without
-    /// knowing the concrete props type.
-    /// </summary>
-    public abstract ConsoleReactiveProps? BaseProps { get; set; }
+    /// <summary>Gets or sets the 1-based column position of the component.</summary>
+    public int X { get; set; }
+
+    /// <summary>Gets or sets the 1-based row position of the component.</summary>
+    public int Y { get; set; }
+
+    /// <summary>Gets or sets the width of the component in columns.</summary>
+    public int Width { get; set; }
+
+    /// <summary>Gets or sets the height of the component in rows.</summary>
+    public int Height { get; set; }
 
     /// <summary>Renders the component to the console at its current position.</summary>
     public abstract void Render();
-
-    /// <summary>
-    /// Invalidates the component's cached render state, causing the next <see cref="Render"/> call
-    /// to proceed even if props and state have not changed. Use after a screen erase to force repaint.
-    /// </summary>
-    public abstract void Invalidate();
 }
 
 /// <summary>
@@ -47,13 +46,6 @@ public abstract class ConsoleReactiveComponent<TProps, TState> : ConsoleReactive
     /// <summary>Gets or sets the component's props (external configuration).</summary>
     public TProps? Props { get; set; }
 
-    /// <inheritdoc/>
-    public override ConsoleReactiveProps? BaseProps
-    {
-        get => this.Props;
-        set => this.Props = (TProps?)value;
-    }
-
     /// <summary>Gets or sets the component's internal state.</summary>
     protected TState? State { get; set; }
 
@@ -81,8 +73,8 @@ public abstract class ConsoleReactiveComponent<TProps, TState> : ConsoleReactive
                 return;
             }
 
-            if (EqualityComparer<TProps>.Default.Equals(this.Props, this._lastRenderedProps)
-                && EqualityComparer<TState>.Default.Equals(this.State, this._lastRenderedState))
+            if (ReferenceEquals(this.Props, this._lastRenderedProps)
+                && ReferenceEquals(this.State, this._lastRenderedState))
             {
                 return;
             }
@@ -94,16 +86,6 @@ public abstract class ConsoleReactiveComponent<TProps, TState> : ConsoleReactive
         }
     }
 
-    /// <inheritdoc/>
-    public override void Invalidate()
-    {
-        lock (this._renderLock)
-        {
-            this._lastRenderedProps = default;
-            this._lastRenderedState = default;
-        }
-    }
-
     /// <summary>
     /// Called by <see cref="Render"/> to perform the actual rendering. Override this in derived classes.
     /// </summary>
@@ -113,23 +95,11 @@ public abstract class ConsoleReactiveComponent<TProps, TState> : ConsoleReactive
 }
 
 /// <summary>
-/// Base record for component props. Provides layout properties (position and size)
-/// and an optional <see cref="Children"/> collection for composing child components.
+/// Base record for component props. Provides an optional <see cref="Children"/> collection
+/// for composing child components.
 /// </summary>
 public record ConsoleReactiveProps
 {
-    /// <summary>Gets the 1-based column position of the component.</summary>
-    public int X { get; init; }
-
-    /// <summary>Gets the 1-based row position of the component.</summary>
-    public int Y { get; init; }
-
-    /// <summary>Gets the width of the component in columns.</summary>
-    public int Width { get; init; }
-
-    /// <summary>Gets the height of the component in rows.</summary>
-    public int Height { get; init; }
-
     /// <summary>Gets the child components to render within this component.</summary>
     public IReadOnlyList<ConsoleReactiveComponent> Children { get; init; } = [];
 }

dotnet/samples/02-agents/Harness/Harness_Shared_Console/Components/AgentModeAndHelp.cs

@@ -43,7 +43,7 @@ public class AgentModeAndHelp : ConsoleReactiveComponent<AgentModeAndHelpProps,
         }
 
         System.Console.Write(AnsiEscapes.SaveCursor);
-        System.Console.Write(AnsiEscapes.MoveAndEraseLine(props.Y));
+        System.Console.Write(AnsiEscapes.MoveAndEraseLine(this.Y));
 
         bool hasMode = props.Mode is not null;
 

dotnet/samples/02-agents/Harness/Harness_Shared_Console/Components/AgentStatus.cs

@@ -35,7 +35,6 @@ public class AgentStatus : ConsoleReactiveComponent<AgentStatusProps, AgentStatu
     ];
 
     private readonly Timer _timer;
-    private AgentStatusProps? _previousProps;
 
     /// <summary>
     /// Initializes a new instance of the <see cref="AgentStatus"/> class.
@@ -86,12 +85,7 @@ public class AgentStatus : ConsoleReactiveComponent<AgentStatusProps, AgentStatu
         }
 
         System.Console.Write(AnsiEscapes.SaveCursor);
-        System.Console.Write(AnsiEscapes.MoveCursor(props.Y, props.X));
-        if (props != this._previousProps)
-        {
-            System.Console.Write(AnsiEscapes.EraseToEndOfLine);
-            this._previousProps = props;
-        }
+        System.Console.Write(AnsiEscapes.MoveAndEraseLine(this.Y));
 
         if (props.ShowSpinner)
         {

dotnet/samples/02-agents/Harness/Harness_Shared_Console/HarnessAppComponent.cs

@@ -371,7 +371,7 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             };
 
             bottomChildHeight = ListSelection.CalculateHeight(listProps);
-            listProps = listProps with { Height = bottomChildHeight };
+            this._listSelection.Height = bottomChildHeight;
             this._listSelection.Props = listProps;
             bottomChild = this._listSelection;
         }
@@ -398,7 +398,8 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             }
 
             bottomChildHeight = TextInput.CalculateHeight(textInputProps, state.ConsoleWidth);
-            textInputProps = textInputProps with { Width = state.ConsoleWidth, Height = bottomChildHeight };
+            this._textInput.Width = state.ConsoleWidth;
+            this._textInput.Height = bottomChildHeight;
             this._textInput.Props = textInputProps;
             bottomChild = this._textInput;
         }
@@ -412,7 +413,8 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             };
 
             bottomChildHeight = TextInput.CalculateHeight(textInputProps, state.ConsoleWidth);
-            textInputProps = textInputProps with { Width = state.ConsoleWidth, Height = bottomChildHeight };
+            this._textInput.Width = state.ConsoleWidth;
+            this._textInput.Height = bottomChildHeight;
             this._textInput.Props = textInputProps;
             bottomChild = this._textInput;
         }
@@ -457,16 +459,6 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             System.Console.Write(AnsiEscapes.EraseScrollbackBuffer);
             this._textScrollPanel.Reset();
             this._resizedSinceLastRender = false;
-
-            // Invalidate all children so they re-render even if props haven't changed
-            this._rule.Invalidate();
-            this._textScrollPanel.Invalidate();
-            this._textPanel.Invalidate();
-            this._queuedPanel.Invalidate();
-            this._agentStatus.Invalidate();
-            this._modeAndHelp.Invalidate();
-            this._textInput.Invalidate();
-            this._listSelection.Invalidate();
         }
 
         this._scrollRegionBottom = scrollBottom;
@@ -478,35 +470,35 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             ? state.ScrollAreaContentItems.Take(state.ScrollAreaContentItems.Count - 1).ToList()
             : [];
 
+        this._textScrollPanel.X = 1;
+        this._textScrollPanel.Y = 1;
+        this._textScrollPanel.Width = state.ConsoleWidth;
+        this._textScrollPanel.Height = scrollBottom;
         this._textScrollPanel.Props = new TextScrollPanelProps
         {
-            X = 1,
-            Y = 1,
-            Width = state.ConsoleWidth,
-            Height = scrollBottom,
             Items = scrollItems,
         };
         this._textScrollPanel.Render();
 
         // Render the text panel for the last (dynamic) item just below the scroll region
+        this._textPanel.X = 1;
+        this._textPanel.Y = scrollBottom + 1;
+        this._textPanel.Width = state.ConsoleWidth;
+        this._textPanel.Height = textPanelHeight;
         this._textPanel.Props = new TextPanelProps
         {
-            X = 1,
-            Y = scrollBottom + 1,
-            Width = state.ConsoleWidth,
-            Height = textPanelHeight,
             Items = lastItems,
         };
         this._textPanel.Render();
 
         // Render queued input items between text panel and agent status
         int queuedPanelY = scrollBottom + textPanelHeight + 1;
+        this._queuedPanel.X = 1;
+        this._queuedPanel.Y = queuedPanelY;
+        this._queuedPanel.Width = state.ConsoleWidth;
+        this._queuedPanel.Height = queuedPanelHeight;
         this._queuedPanel.Props = new TextPanelProps
         {
-            X = 1,
-            Y = queuedPanelY,
-            Width = state.ConsoleWidth,
-            Height = queuedPanelHeight,
             Items = state.QueuedItems,
         };
         this._queuedPanel.Render();
@@ -515,41 +507,32 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
         int agentStatusY = queuedPanelY + queuedPanelHeight;
         if (showStatusAndHelp)
         {
-            this._agentStatus.Props = agentStatusProps with
-            {
-                X = 1,
-                Y = agentStatusY,
-                Width = state.ConsoleWidth,
-                Height = agentStatusHeight,
-            };
+            this._agentStatus.X = 1;
+            this._agentStatus.Y = agentStatusY;
+            this._agentStatus.Width = state.ConsoleWidth;
+            this._agentStatus.Height = agentStatusHeight;
+            this._agentStatus.Props = agentStatusProps;
             this._agentStatus.Render();
         }
 
         // Render the bottom rule + child below the agent status
-        this._rule.Props = ruleProps with
-        {
-            X = 1,
-            Y = agentStatusY + agentStatusHeight,
-        };
+        this._rule.X = 1;
+        this._rule.Y = agentStatusY + agentStatusHeight;
+        this._rule.Props = ruleProps;
         this._rule.Render();
 
         // Render the mode-and-help line below the bottom rule
         if (showStatusAndHelp)
         {
-            int modeAndHelpY = agentStatusY + agentStatusHeight + ruleHeight;
-            this._modeAndHelp.Props = modeAndHelpProps with
-            {
-                X = 1,
-                Y = modeAndHelpY,
-                Width = state.ConsoleWidth,
-                Height = modeAndHelpHeight,
-            };
+            int modeAndHelpY = this._rule.Y + ruleHeight;
+            this._modeAndHelp.X = 1;
+            this._modeAndHelp.Y = modeAndHelpY;
+            this._modeAndHelp.Width = state.ConsoleWidth;
+            this._modeAndHelp.Height = modeAndHelpHeight;
+            this._modeAndHelp.Props = modeAndHelpProps;
             this._modeAndHelp.Render();
         }
 
-        // Clear the bottom padding line
-        System.Console.Write(AnsiEscapes.MoveAndEraseLine(state.ConsoleHeight));
-
         // Position cursor for natural typing appearance
         this.PositionCursor(state);
     }
@@ -563,7 +546,7 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             int textWidth = state.ConsoleWidth - promptLength;
             int textLength = state.InputText.Length;
 
-            int textInputY = (this._rule.Props?.Y ?? 0) + 1;
+            int textInputY = this._rule.Y + 1;
 
             if (textWidth <= 0 || textLength == 0)
             {
@@ -581,7 +564,7 @@ public class HarnessAppComponent : ConsoleReactiveComponent<ConsoleReactiveProps
             && state.ListSelectionIndex == state.ListSelectionOptions.Count)
         {
             int titleLines = state.ListSelectionTitle?.Split('\n').Length ?? 0;
-            int customOptionY = (this._rule.Props?.Y ?? 0) + 1 + titleLines + state.ListSelectionOptions.Count;
+            int customOptionY = this._rule.Y + 1 + titleLines + state.ListSelectionOptions.Count;
             int cursorCol = 2 + state.ListSelectionCustomInputText.Length + 1;
             System.Console.Write(AnsiEscapes.MoveCursor(customOptionY, cursorCol));
         }

dotnet/samples/02-agents/Harness/Harness_Shared_Console/HarnessConsole.cs

@@ -1,6 +1,5 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-using System.Text;
 using Harness.ConsoleReactiveComponents;
 using Microsoft.Agents.AI;
 
@@ -25,8 +24,6 @@ public static class HarnessConsole
     {
         options ??= new();
 
-        System.Console.OutputEncoding = Encoding.UTF8;
-
         // Null means use defaults; an explicit (possibly empty) list means use exactly what was provided.
         var observers = options.Observers
             ?? HarnessConsoleOptions.BuildDefaultObservers();
@@ -36,9 +33,7 @@ public static class HarnessConsole
         var modeProvider = agent.GetService<AgentModeProvider>();
         var messageInjector = agent.GetService<MessageInjectingChatClient>();
 
-        AgentSession session = options.SessionFactory is not null
-            ? await options.SessionFactory(agent)
-            : await agent.CreateSessionAsync();
+        AgentSession session = await agent.CreateSessionAsync();
 
         using var component = new HarnessAppComponent(
             placeholder: userPrompt,
@@ -68,7 +63,6 @@ public static class HarnessConsole
 
         System.Console.ResetColor();
         System.Console.Write(AnsiEscapes.ResetScrollRegion);
-        System.Console.Write(AnsiEscapes.EraseScrollbackBuffer);
         System.Console.Write(AnsiEscapes.EraseEntireScreen);
         System.Console.Write(AnsiEscapes.MoveCursor(1, 1));
         System.Console.WriteLine("Goodbye!");

dotnet/samples/02-agents/Harness/Harness_Shared_Console/HarnessConsoleOptions.cs

@@ -45,12 +45,6 @@ public class HarnessConsoleOptions
     /// </summary>
     public Dictionary<string, ConsoleColor> ModeColors { get; set; } = new(DefaultModeColors, StringComparer.OrdinalIgnoreCase);
 
-    /// <summary>
-    /// Gets or sets an optional factory for creating the <see cref="AgentSession"/>.
-    /// When <see langword="null"/> (the default), <see cref="AIAgent.CreateSessionAsync"/> is used.
-    /// </summary>
-    public Func<AIAgent, Task<AgentSession>>? SessionFactory { get; set; }
-
     /// <summary>
     /// Creates the default set of observers without planning support.
     /// Includes tool call display, tool approval, error display, reasoning display,

dotnet/samples/02-agents/Harness/Harness_Step04_CodeExecution/Harness_Step04_CodeExecution.csproj

@@ -1,29 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <OutputType>Exe</OutputType>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-
-    <Nullable>enable</Nullable>
-    <ImplicitUsings>enable</ImplicitUsings>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Azure.AI.Projects" />
-    <PackageReference Include="Azure.Identity" />
-    <PackageReference Include="Hyperlight.HyperlightSandbox.Guest.Python" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Harness\Microsoft.Agents.AI.Harness.csproj" />
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Hyperlight\Microsoft.Agents.AI.Hyperlight.csproj" />
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
-    <ProjectReference Include="..\Harness_Shared_Console\Harness_Shared_Console.csproj" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <Content Include="skills\**\*" CopyToOutputDirectory="PreserveNewest" />
-  </ItemGroup>
-
-</Project>

dotnet/samples/02-agents/Harness/Harness_Step04_CodeExecution/Program.cs

@@ -1,122 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-// This sample demonstrates a HarnessAgent with ALL features enabled, plus:
-// - Hyperlight CodeAct (HyperlightCodeActProvider) for sandboxed Python code execution
-// - Skills (AgentSkillsProvider) discovering a local "regex-tester" skill
-//
-// The agent can plan tasks with todos, manage modes, store memories, read/write files,
-// search the web, approve sensitive tools, discover and use skills, and execute arbitrary
-// Python code in a Hyperlight sandbox — all pre-configured by the HarnessAgent.
-//
-// Try asking: "Help me write a regex that matches valid email addresses, then test it."
-//
-// Special commands:
-//   /todos  — Display the current todo list without invoking the agent.
-//   /mode   — Get or set the current agent mode.
-//   /exit   — End the session.
-
-#pragma warning disable OPENAI001 // Suppress experimental API warnings for Responses API usage.
-#pragma warning disable MAAI001  // Suppress experimental API warnings for Agents AI experiments.
-
-using System.ClientModel.Primitives;
-using Azure.AI.Projects;
-using Azure.Identity;
-using Harness.Shared.Console;
-using HyperlightSandbox.Guest.Python;
-using Microsoft.Agents.AI;
-using Microsoft.Agents.AI.Hyperlight;
-using Microsoft.Extensions.AI;
-
-var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
-var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5.4";
-
-const int MaxContextWindowTokens = 1_050_000;
-const int MaxOutputTokens = 128_000;
-const string TracingSourceName = "Harness.CodeExecution";
-
-// Set up OpenTelemetry tracing that writes spans to a text file.
-using var tracerProvider = HarnessTracing.CreateFileTracerProvider(TracingSourceName);
-
-// Create the HyperlightCodeActProvider with the Python/Wasm backend.
-// The guest module path is resolved automatically from the Hyperlight.HyperlightSandbox.Guest.Python NuGet package.
-using var codeAct = new HyperlightCodeActProvider(
-    HyperlightCodeActProviderOptions.CreateForWasm(PythonGuestModule.GetModulePath()));
-
-var instructions =
-    """
-    ## Technical Assistant Instructions
-
-    You are a code-powered technical assistant. You can execute Python code in a sandboxed environment
-    to solve problems precisely rather than guessing. You also have access to skills that provide
-    structured workflows for specific technical tasks.
-
-    ### Code Execution
-
-    When a problem requires computation, validation, or testing:
-    - Write Python code and use `execute_code` to run it in the sandbox.
-    - Always verify results by running the code rather than reasoning about what would happen.
-    - If code fails, read the error message carefully, fix the issue, and retry.
-
-    ### Skills
-
-    You have access to discoverable skills. When a task matches a skill's description:
-    - Follow the skill's instructions carefully.
-    - Use the skill's reference materials for context.
-    - Combine the skill's workflow with code execution when appropriate.
-
-    ### Planning and Research
-
-    For complex tasks:
-    - Break the problem into steps using your todo list.
-    - Research background information using web search when needed.
-    - Save important findings to file memory for later reference.
-
-    ### Presenting Results
-
-    - Show your work: include the code you ran and its output.
-    - Explain what each part of your solution does.
-    - If applicable, save final results to file memory.
-    """;
-
-// Create the agent with ALL HarnessAgent features enabled plus Hyperlight CodeAct.
-// No Disable* flags are set — TodoProvider, AgentModeProvider, FileMemory, FileAccess,
-// ToolApproval, WebSearch, and AgentSkillsProvider are all active.
-AIAgent agent =
-    new AIProjectClient(
-        new Uri(endpoint),
-        new DefaultAzureCredential(),
-        new AIProjectClientOptions { RetryPolicy = new ClientRetryPolicy(3) })
-    .GetProjectOpenAIClient()
-    .GetResponsesClient()
-    .AsIChatClient(deploymentName)
-    .AsHarnessAgent(MaxContextWindowTokens, MaxOutputTokens, new HarnessAgentOptions
-    {
-        Name = "CodeExecutionAgent",
-        Description = "A technical assistant with sandboxed code execution and skill-based workflows.",
-        OpenTelemetrySourceName = TracingSourceName,
-        // Point the file memory at a local folder for persistent memory across sessions.
-        FileMemoryStore = new FileSystemAgentFileStore(Path.Combine(AppContext.BaseDirectory, "agent-files")),
-        // Add the HyperlightCodeActProvider so the agent can execute Python code in a sandbox.
-        AIContextProviders = [codeAct],
-        ChatOptions = new ChatOptions
-        {
-            Instructions = instructions,
-            MaxOutputTokens = MaxOutputTokens,
-            Reasoning = new() { Effort = ReasoningEffort.Medium },
-        },
-    });
-
-// Run the interactive console session using the shared HarnessConsole helper.
-await HarnessConsole.RunAgentAsync(
-    agent,
-    userPrompt: "Ask me a technical question, or try: \"Help me write a regex that matches valid email addresses.\"",
-    new HarnessConsoleOptions
-    {
-        Observers = HarnessConsoleOptions.BuildObserversWithPlanning(
-            agent,
-            planModeName: "plan",
-            executionModeName: "execute",
-            maxContextWindowTokens: MaxContextWindowTokens,
-            maxOutputTokens: MaxOutputTokens),
-        CommandHandlers = HarnessConsoleOptions.BuildDefaultCommandHandlers(agent),
-    });

dotnet/samples/02-agents/Harness/Harness_Step04_CodeExecution/README.md

@@ -1,51 +0,0 @@
-# Harness Step 04 — Code Execution (Hyperlight + Skills)
-
-This sample demonstrates a HarnessAgent with **all features enabled**, plus:
-
-- **Hyperlight CodeAct** — sandboxed Python code execution via `execute_code` (requires KVM)
-- **Skills** — file-based skill discovery (a `regex-tester` skill is included)
-
-The agent can plan tasks, manage modes, store memories, read/write files, search the web, approve sensitive operations, discover and use skills, and execute arbitrary Python code — all pre-configured by the HarnessAgent.
-
-## Prerequisites
-
-- .NET 10 SDK
-- An Azure AI Foundry project endpoint
-- KVM-capable host (the Hyperlight sandbox runs code in micro-VMs)
-
-## Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `AZURE_AI_PROJECT_ENDPOINT` | Your Azure AI Foundry project endpoint |
-| `AZURE_AI_MODEL_DEPLOYMENT_NAME` | Model deployment name (default: `gpt-5.4`) |
-
-## Running
-
-```bash
-dotnet run
-```
-
-## What to Try
-
-- **Regex testing**: "Help me write a regex that matches valid email addresses, then test it against some examples."
-- **Code execution**: "Calculate the first 20 prime numbers using the Sieve of Eratosthenes."
-- **Skill + code combo**: "I need a regex for ISO 8601 dates — test it thoroughly with edge cases."
-
-## Included Skill
-
-The `skills/regex-tester/` skill instructs the agent to validate regex patterns by executing Python test code in the Hyperlight sandbox. It includes a regex cheatsheet as reference material.
-
-## Features Enabled
-
-| Feature | Description |
-|---------|-------------|
-| TodoProvider | Task planning and tracking (`/todos` command) |
-| AgentModeProvider | Mode switching (`/mode` command) |
-| FileMemoryProvider | Persistent memory stored as files |
-| FileAccessProvider | Read/write files in a working directory |
-| ToolApproval | Don't-ask-again approval for sensitive tools |
-| WebSearch | Built-in hosted web search |
-| AgentSkillsProvider | Discovers and uses skills from the `skills/` folder |
-| HyperlightCodeActProvider | Sandboxed Python execution via `execute_code` |
-| OpenTelemetry | Trace logging to a text file |

dotnet/samples/02-agents/Harness/Harness_Step04_CodeExecution/skills/regex-tester/SKILL.md

@@ -1,36 +0,0 @@
----
-name: regex-tester
-description: Validate, test, and debug regular expressions by executing them against sample inputs. Use when asked to build, verify, or explain a regex pattern.
----
-
-## Usage
-
-When the user asks you to create, validate, or debug a regular expression:
-
-1. **Understand the requirement** — clarify what the pattern should match and what it should reject.
-2. **Consult the cheatsheet** — review `references/regex-cheatsheet.md` for syntax reminders if needed.
-3. **Write and execute test code** — use the `execute_code` tool to run Python code that:
-   - Compiles the regex with `re.compile()`
-   - Tests it against a set of positive examples (should match) and negative examples (should not match)
-   - Extracts and displays any capturing groups
-   - Reports pass/fail for each test case
-4. **Iterate** — if any test fails, refine the pattern and re-run until all cases pass.
-5. **Present the result** — give the user the final pattern, explain what each part does, and show the test results.
-
-## Example Test Script
-
-```python
-import re
-
-pattern = re.compile(r'^[\w.+-]+@[\w-]+\.[\w.-]+$')
-
-positives = ["user@example.com", "first.last+tag@sub.domain.org"]
-negatives = ["@missing.com", "no-at-sign", "spaces in@address.com"]
-
-for s in positives:
-    assert pattern.match(s), f"FAIL: expected match for '{s}'"
-for s in negatives:
-    assert not pattern.match(s), f"FAIL: expected no match for '{s}'"
-
-print("All tests passed!")
-```

dotnet/samples/02-agents/Harness/Harness_Step04_CodeExecution/skills/regex-tester/references/regex-cheatsheet.md

@@ -1,97 +0,0 @@
-# Regex Quick Reference (Python `re` module)
-
-## Character Classes
-
-| Pattern | Matches |
-|---------|---------|
-| `.`     | Any character except newline |
-| `\d`    | Digit `[0-9]` |
-| `\D`    | Non-digit |
-| `\w`    | Word character `[a-zA-Z0-9_]` |
-| `\W`    | Non-word character |
-| `\s`    | Whitespace `[ \t\n\r\f\v]` |
-| `\S`    | Non-whitespace |
-| `[abc]` | Any of a, b, or c |
-| `[^abc]`| Any character except a, b, c |
-| `[a-z]` | Range: a through z |
-
-## Quantifiers
-
-| Pattern | Meaning |
-|---------|---------|
-| `*`     | 0 or more (greedy) |
-| `+`     | 1 or more (greedy) |
-| `?`     | 0 or 1 (greedy) |
-| `{n}`   | Exactly n |
-| `{n,}`  | n or more |
-| `{n,m}` | Between n and m |
-| `*?`, `+?`, `??` | Non-greedy versions |
-
-## Anchors
-
-| Pattern | Meaning |
-|---------|---------|
-| `^`     | Start of string (or line with `re.MULTILINE`) |
-| `$`     | End of string (or line with `re.MULTILINE`) |
-| `\b`    | Word boundary |
-| `\B`    | Non-word boundary |
-
-## Groups and Backreferences
-
-| Pattern | Meaning |
-|---------|---------|
-| `(...)` | Capturing group |
-| `(?:...)`| Non-capturing group |
-| `(?P<name>...)` | Named group |
-| `\1`    | Backreference to group 1 |
-| `(?=...)` | Positive lookahead |
-| `(?!...)` | Negative lookahead |
-| `(?<=...)` | Positive lookbehind |
-| `(?<!...)` | Negative lookbehind |
-
-## Flags
-
-| Flag | Effect |
-|------|--------|
-| `re.IGNORECASE` / `re.I` | Case-insensitive matching |
-| `re.MULTILINE` / `re.M`  | `^`/`$` match line boundaries |
-| `re.DOTALL` / `re.S`     | `.` matches newline |
-| `re.VERBOSE` / `re.X`    | Allow comments and whitespace |
-
-## Common Patterns
-
-| Use Case | Pattern |
-|----------|---------|
-| Email (simple) | `^[\w.+-]+@[\w-]+\.[\w.-]+$` |
-| IPv4 address | `^\d{1,3}(\.\d{1,3}){3}$` |
-| ISO date | `^\d{4}-\d{2}-\d{2}$` |
-| URL (http/https) | `^https?://[^\s/$.?#].[^\s]*$` |
-| Phone (US) | `^(\+1)?[-.\s]?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}$` |
-
-## Python API
-
-```python
-import re
-
-# Test if a string matches
-re.match(r'pattern', "string")       # match at start
-re.search(r'pattern', "string")      # match anywhere
-re.fullmatch(r'pattern', "string")   # match entire string
-
-# Find all matches
-re.findall(r'\d+', "abc 123 def 456")  # ['123', '456']
-
-# Named groups
-m = re.match(r'(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})', "2025-01-15")
-m.group('year')   # '2025'
-
-# Replace
-re.sub(r'\d+', 'X', "abc 123 def")   # 'abc X def'
-
-# Split
-re.split(r',+', "a,b,,c")            # ['a', 'b', 'c']
-
-# Compile for reuse
-pattern = re.compile(r'^\d{4}-\d{2}-\d{2}$')
-pattern.match("2025-01-15")           # Match object
-```

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

@@ -0,0 +1,838 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System;
+using System.Collections.Generic;
+using System.ComponentModel;
+using System.Linq;
+using System.Runtime.CompilerServices;
+using System.Text.Json;
+using System.Threading;
+using System.Threading.Tasks;
+using FluentAssertions;
+using Microsoft.Agents.AI.Workflows.Checkpointing;
+using Microsoft.Agents.AI.Workflows.InProc;
+using Microsoft.Extensions.AI;
+
+namespace Microsoft.Agents.AI.Workflows.UnitTests;
+
+/// <summary>
+/// Repro tests for issue #5350: <c>ToolApprovalRequestContent.ToolCall</c> reportedly loses its
+/// concrete <see cref="FunctionCallContent"/> type after being persisted via a
+/// <c>JsonCheckpointStore</c>-backed <c>CheckpointManager</c> and restored on resume.
+///
+/// These tests bypass the OP's SQL-backed store and HITL agent setup and directly exercise
+/// the same JSON pipeline used by the checkpoint path (<see cref="JsonMarshaller"/> ->
+/// <see cref="PortableValueConverter"/> -> <see cref="WorkflowsJsonUtilities"/>.DefaultOptions,
+/// which chains through AgentAbstractionsJsonUtilities -> AIJsonUtilities), at progressively
+/// more end-to-end layers up to a full <c>CheckpointManager.CreateJson(...)</c> +
+/// <c>RunStreamingAsync</c> / <c>ResumeStreamingAsync</c> cycle.
+///
+/// At the time of writing all of these tests <b>pass</b>, which provides counter-evidence
+/// against the root-cause hypothesis stated in the issue body (missing polymorphism
+/// metadata / serializer-options chain). See
+/// <c>docs/working/issue-5350-root-cause-validation-plan.md</c> for the full investigation
+/// plan that builds on this baseline.
+/// </summary>
+public class ToolApprovalRequestCheckpointReproTests
+{
+    private const string RequestId = "req-1";
+    private const string CallId = "call-1";
+    private const string FunctionName = "DoTheThing";
+
+    private static FunctionCallContent MakeFunctionCall() => new(
+        callId: CallId,
+        name: FunctionName,
+        arguments: new Dictionary<string, object?> { ["x"] = 42 });
+
+    private static ToolApprovalRequestContent MakeApprovalRequest()
+        => new(RequestId, MakeFunctionCall());
+
+    /// <summary>
+    /// Direct round-trip of a <see cref="ToolApprovalRequestContent"/> through the same
+    /// <see cref="JsonMarshaller"/> used by <c>CheckpointManager.CreateJson(...)</c>.
+    ///
+    /// Per the issue, after deserialization the <c>ToolCall</c> property (declared as the
+    /// abstract base <c>ToolCallContent</c>) is expected to remain a
+    /// <see cref="FunctionCallContent"/>. If polymorphism is preserved, this test passes;
+    /// if the discriminator is dropped on the wire or on read, <c>ToolCall</c> comes back
+    /// as something other than <see cref="FunctionCallContent"/> and FICC's pattern match
+    /// (<c>tarc.ToolCall is FunctionCallContent { InformationalOnly: false }</c>) silently
+    /// skips the approval pair.
+    /// </summary>
+    [Fact]
+    public void Repro_5350_ToolApprovalRequestContent_DirectJsonMarshallerRoundtrip_PreservesFunctionCallContent()
+    {
+        ToolApprovalRequestContent original = MakeApprovalRequest();
+
+        ToolApprovalRequestContent roundTripped = JsonSerializationTests.RunJsonRoundtrip(original);
+
+        roundTripped.Should().NotBeNull();
+        roundTripped.RequestId.Should().Be(RequestId);
+        roundTripped.ToolCall.Should().NotBeNull();
+
+        // This is the assertion that, per issue #5350, fails on resume.
+        roundTripped.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "ToolApprovalRequestContent.ToolCall must round-trip as its concrete FunctionCallContent type, " +
+            "otherwise FunctionInvokingChatClient.ExtractAndRemoveApprovalRequestsAndResponses will silently " +
+            "skip the approval pair after a checkpoint resume (issue #5350).");
+
+        FunctionCallContent? fcc = roundTripped.ToolCall as FunctionCallContent;
+        fcc!.CallId.Should().Be(CallId);
+        fcc.Name.Should().Be(FunctionName);
+    }
+
+    /// <summary>
+    /// Same round-trip as above, but wrapped in a <see cref="PortableValue"/>. This more closely
+    /// mirrors how the workflow runtime stores externally-visible request payloads in a checkpoint
+    /// (<see cref="PortableMessageEnvelope"/> / <see cref="PortableValue"/>). The
+    /// <see cref="PortableValueConverter"/> serializes the inner value with
+    /// <c>marshaller.Marshal(value.Value, value.Value.GetType())</c>, so on the write side the
+    /// runtime type is used (which should include the discriminator), and on the read side the
+    /// inner value is materialized as a <see cref="JsonElement"/> then re-deserialized as the
+    /// declared type via <see cref="PortableValue.As{T}"/>.
+    /// </summary>
+    [Fact]
+    public void Repro_5350_ToolApprovalRequestContent_WrappedInPortableValue_PreservesFunctionCallContent()
+    {
+        PortableValue original = new(MakeApprovalRequest());
+
+        PortableValue result = JsonSerializationTests.RunJsonRoundtrip(original);
+
+        ToolApprovalRequestContent? extracted = result.As<ToolApprovalRequestContent>();
+        extracted.Should().NotBeNull();
+        extracted!.RequestId.Should().Be(RequestId);
+        extracted.ToolCall.Should().NotBeNull();
+        extracted.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "PortableValue-wrapped ToolApprovalRequestContent must preserve the concrete " +
+            "FunctionCallContent on the ToolCall property after checkpoint round-trip (issue #5350).");
+    }
+
+    /// <summary>
+    /// Round-trip the <see cref="ToolApprovalRequestContent"/> as the payload of an
+    /// <see cref="ExternalRequest"/>, which is the actual on-the-wire shape for HITL approval
+    /// requests flowing out of a workflow. This is the closest serializer-only proxy for what
+    /// happens when the issue reporter calls
+    /// <c>request.TryGetDataAs&lt;ToolApprovalRequestContent&gt;()</c> after
+    /// <c>InProcessExecution.ResumeStreamingAsync(...)</c>.
+    /// </summary>
+    [Fact]
+    public void Repro_5350_ToolApprovalRequestContent_AsExternalRequestData_PreservesFunctionCallContent()
+    {
+        RequestPort<ToolApprovalRequestContent, ToolApprovalResponseContent> port
+            = RequestPort.Create<ToolApprovalRequestContent, ToolApprovalResponseContent>("Approval");
+
+        ExternalRequest original = ExternalRequest.Create(port, MakeApprovalRequest(), RequestId);
+
+        ExternalRequest result = JsonSerializationTests.RunJsonRoundtrip(original);
+
+        ToolApprovalRequestContent? extracted = result.Data.As<ToolApprovalRequestContent>();
+        extracted.Should().NotBeNull();
+        extracted!.ToolCall.Should().NotBeNull();
+        extracted.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "ExternalRequest.Data restored from a JSON checkpoint must preserve the concrete " +
+            "FunctionCallContent on ToolApprovalRequestContent.ToolCall (issue #5350).");
+    }
+
+    /// <summary>
+    /// Stability check: run the direct round-trip many times in a row to demonstrate that
+    /// the failure mode (if present) is deterministic and not a flaky/JIT-order artifact.
+    /// </summary>
+    [Fact]
+    public void Repro_5350_DirectJsonMarshallerRoundtrip_IsDeterministic()
+    {
+        for (int i = 0; i < 25; i++)
+        {
+            ToolApprovalRequestContent original = MakeApprovalRequest();
+            ToolApprovalRequestContent roundTripped = JsonSerializationTests.RunJsonRoundtrip(original);
+
+            roundTripped.ToolCall.Should().BeOfType<FunctionCallContent>(
+                $"iteration {i}: ToolCall must consistently round-trip as FunctionCallContent");
+        }
+    }
+
+    /// <summary>
+    /// End-to-end checkpoint -> resume repro using the actual <c>CheckpointManager.CreateJson(...)</c>
+    /// path that the issue reporter uses. A trivial workflow whose entry point is a
+    /// <c>RequestPort&lt;ToolApprovalRequestContent, ToolApprovalResponseContent&gt;</c> emits a
+    /// pending external request containing a <see cref="FunctionCallContent"/>. We then:
+    ///   1. checkpoint the run while the request is pending,
+    ///   2. resume from the checkpoint via a fresh <c>InProcessExecution</c>,
+    ///   3. read the re-emitted <see cref="RequestInfoEvent"/>, and
+    ///   4. assert that <c>request.Data.As&lt;ToolApprovalRequestContent&gt;().ToolCall</c> is
+    ///      still a <see cref="FunctionCallContent"/>.
+    ///
+    /// This is the closest serializer-and-runtime repro for issue #5350 that does not require a
+    /// real <c>ChatClientAgent</c> + <c>ApprovalRequiredAIFunction</c>.
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_EndToEnd_JsonCheckpointResume_PreservesFunctionCallContentAsync()
+    {
+        RequestPort<ToolApprovalRequestContent, ToolApprovalResponseContent> requestPort
+            = RequestPort.Create<ToolApprovalRequestContent, ToolApprovalResponseContent>("ApprovalPort");
+        ForwardMessageExecutor<ToolApprovalResponseContent> processor = new("Processor");
+
+        Workflow workflow = new WorkflowBuilder(requestPort)
+            .AddEdge(requestPort, processor)
+            .Build();
+
+        CheckpointManager checkpointManager = CheckpointManager.CreateJson(new InMemoryJsonStore());
+        InProcessExecutionEnvironment env = InProcessExecution.OffThread;
+
+        ToolApprovalRequestContent input = MakeApprovalRequest();
+        CheckpointInfo? checkpoint = null;
+        ExternalRequest? originalPendingRequest = null;
+
+        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
+                                                      .RunStreamingAsync(workflow, input))
+        {
+            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false))
+            {
+                if (evt is RequestInfoEvent requestInfo)
+                {
+                    originalPendingRequest ??= requestInfo.Request;
+                }
+
+                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
+                {
+                    checkpoint = cp;
+                }
+            }
+        }
+
+        originalPendingRequest.Should().NotBeNull("the workflow should have emitted the approval request");
+        checkpoint.Should().NotBeNull("a checkpoint should have been produced while the request was pending");
+
+        // Sanity: the pre-checkpoint payload should be a FunctionCallContent.
+        ToolApprovalRequestContent? preCheckpoint = originalPendingRequest!.Data.As<ToolApprovalRequestContent>();
+        preCheckpoint.Should().NotBeNull();
+        preCheckpoint!.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "the pre-checkpoint pending request payload must already be a FunctionCallContent");
+
+        // Resume from the checkpoint and capture the re-emitted request.
+        await using StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
+                                                    .ResumeStreamingAsync(workflow, checkpoint!);
+
+        ExternalRequest? resumedPendingRequest = null;
+        using CancellationTokenSource cts = new(TimeSpan.FromSeconds(10));
+        await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
+        {
+            if (evt is RequestInfoEvent requestInfo)
+            {
+                resumedPendingRequest ??= requestInfo.Request;
+            }
+        }
+
+        resumedPendingRequest.Should().NotBeNull("the resumed workflow should re-emit the pending request");
+
+        ToolApprovalRequestContent? postResume = resumedPendingRequest!.Data.As<ToolApprovalRequestContent>();
+        postResume.Should().NotBeNull(
+            "ExternalRequest.Data.As<ToolApprovalRequestContent>() should materialize the payload after a JSON checkpoint resume");
+
+        // The assertion that the issue reporter says fails.
+        postResume!.ToolCall.Should().NotBeNull();
+        postResume.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "after CheckpointManager.CreateJson round-trip via ResumeStreamingAsync, " +
+            "ToolApprovalRequestContent.ToolCall must still be a FunctionCallContent so that " +
+            "FunctionInvokingChatClient's pattern match (`tarc.ToolCall is FunctionCallContent`) continues to fire " +
+            "(issue #5350).");
+    }
+
+    /// <summary>
+    /// Captures the raw JSON produced for a <see cref="ToolApprovalRequestContent"/> by the
+    /// checkpoint marshaller. This test always passes; it exists to make the on-the-wire shape
+    /// visible in test output / debugger when investigating issue #5350 (e.g. to confirm the
+    /// <c>"$type": "functionCall"</c> discriminator is or is not present for the inner
+    /// <c>toolCall</c> property).
+    /// </summary>
+    [Fact]
+    public void Repro_5350_CaptureWireFormat_ForInspection()
+    {
+        JsonMarshaller marshaller = new();
+
+        JsonElement element = marshaller.Marshal(MakeApprovalRequest());
+        string serialized = element.GetRawText();
+
+        // Always-true assertion — purpose of this test is to expose the wire format.
+        serialized.Should().NotBeNullOrEmpty();
+        serialized.Should().Contain(CallId, "the call id should be present in the serialized form");
+    }
+
+    /// <summary>
+    /// Maximal end-to-end repro for issue #5350 using the same shape as the OP's reported
+    /// scenario (pattern "B" in the GroupChatToolApproval sample), but with a single
+    /// <see cref="ChatClientAgent"/> bound directly into a <see cref="WorkflowBuilder"/>
+    /// (no orchestration), and with a real <see cref="ApprovalRequiredAIFunction"/>-wrapped
+    /// tool that the agent actually attempts to call. The test:
+    /// <list type="number">
+    /// <item>builds a <see cref="ChatClientAgent"/> over a <see cref="MockChatClient"/> that
+    /// returns a <see cref="FunctionCallContent"/> on the first turn and a final assistant
+    /// text on the second turn (so <see cref="FunctionInvokingChatClient"/> converts the FCC
+    /// to a <see cref="ToolApprovalRequestContent"/> and surfaces it as a workflow
+    /// <see cref="RequestInfoEvent"/>),</item>
+    /// <item>persists checkpoints via the OP's exact path —
+    /// <c>CheckpointManager.CreateJson(InMemoryJsonStore)</c> +
+    /// <c>InProcessExecutionEnvironment.WithCheckpointing(...).RunStreamingAsync(...)</c> —
+    /// so every checkpoint is round-tripped through the same <see cref="JsonMarshaller"/> +
+    /// <see cref="PortableValueConverter"/> pipeline the OP's SQL-backed store uses,</item>
+    /// <item>validates that the first-run <see cref="RequestInfoEvent.Request"/> carries a
+    /// <see cref="ToolApprovalRequestContent"/> whose <c>ToolCall</c> is a
+    /// <see cref="FunctionCallContent"/>,</item>
+    /// <item>disposes the run and resumes from the last <see cref="SuperStepCompletedEvent"/>
+    /// checkpoint via <see cref="InProcessExecutionEnvironment.ResumeStreamingAsync"/>,</item>
+    /// <item>validates the re-emitted <see cref="RequestInfoEvent.Request"/> still carries a
+    /// <see cref="ToolApprovalRequestContent"/> whose <c>ToolCall</c> is a
+    /// <see cref="FunctionCallContent"/> — this is the assertion the OP claims fails,</item>
+    /// <item>sends an approval response back into the resumed run and asserts the wrapped
+    /// function is actually invoked (counter increments) and the workflow completes with a
+    /// final assistant message.</item>
+    /// </list>
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_EndToEnd_ChatClientAgent_WithApprovalRequiredTool_JsonCheckpointResume_PreservesFunctionCallContentAndInvokesToolAsync()
+    {
+        // Arrange — counting tool wrapped for approval
+        int invocationCount = 0;
+        const string ToolName = "GetWeather";
+        const string ToolResultText = "Sunny, 22°C";
+
+        AIFunction underlyingTool = AIFunctionFactory.Create(
+            ([Description("City to look up")] string city) =>
+            {
+                Interlocked.Increment(ref invocationCount);
+                return ToolResultText;
+            },
+            name: ToolName,
+            description: "Gets the weather for the given city");
+
+        ApprovalRequiredAIFunction approvalTool = new(underlyingTool);
+
+        // Arrange — mock chat client that turn-1 emits an FCC for the approval-required tool,
+        // turn-2 (after FunctionInvokingChatClient processes the approval + invokes the tool +
+        // appends a FunctionResultContent) emits a final assistant text.
+        const string ToolCallId = "call-1";
+        const string FinalAssistantText = "The weather in Amsterdam is sunny and 22°C.";
+        int chatCallIndex = 0;
+        List<List<ChatMessage>> capturedInputs = new();
+
+        MockChatClient mockChatClient = new((messages, options) =>
+        {
+            // Capture a snapshot of the inputs the agent passed in for this service call so the
+            // test can later assert the FunctionResultContent flowed back to the model.
+            capturedInputs.Add(new List<ChatMessage>(messages));
+
+            int index = Interlocked.Increment(ref chatCallIndex) - 1;
+            return index switch
+            {
+                0 => new ChatResponse(new ChatMessage(ChatRole.Assistant,
+                    [new FunctionCallContent(
+                        callId: ToolCallId,
+                        name: ToolName,
+                        arguments: new Dictionary<string, object?> { ["city"] = "Amsterdam" })])),
+                _ => new ChatResponse(new ChatMessage(ChatRole.Assistant, FinalAssistantText)),
+            };
+        });
+
+        ChatClientAgent agent = new(
+            mockChatClient,
+            instructions: "You are a weather agent.",
+            name: "WeatherAgent",
+            tools: [approvalTool]);
+
+        // Arrange — single-agent workflow. The AIAgent is auto-promoted to an ExecutorBinding
+        // via the implicit operator on ExecutorBinding.
+        Workflow workflow = new WorkflowBuilder(agent).Build();
+
+        // Arrange — JSON checkpoint manager backed by an in-memory JSON store. This mirrors
+        // the OP's "JsonCheckpointStore-backed CheckpointManager.CreateJson(...)" path —
+        // every checkpoint is round-tripped through the same JsonMarshaller +
+        // PortableValueConverter that the OP's SQL-backed store uses, just without the
+        // disk/SQL hop.
+        CheckpointManager checkpointManager = CheckpointManager.CreateJson(new InMemoryJsonStore());
+
+        InProcessExecutionEnvironment env = InProcessExecution.OffThread;
+        List<ChatMessage> inputMessages = [new(ChatRole.User, "What's the weather in Amsterdam?")];
+
+        // Act 1 — run until we see the approval request, then capture the latest checkpoint.
+        ExternalRequest? firstRunRequest = null;
+        CheckpointInfo? checkpoint = null;
+
+        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
+                                                      .RunStreamingAsync(workflow, inputMessages))
+        {
+            // Trigger an actual turn — without a TurnToken the AIAgentHostExecutor will not
+            // invoke the agent. This matches the GroupChatToolApproval sample and the
+            // StreamAsyncWithTurnTokenShouldExecuteWorkflow pattern in InProcessExecutionTests.
+            (await firstRun.TrySendMessageAsync(new TurnToken(emitEvents: false)))
+                .Should().BeTrue("the workflow should accept a TurnToken");
+
+            using CancellationTokenSource cts = new(TimeSpan.FromSeconds(30));
+            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
+            {
+                if (evt is RequestInfoEvent requestInfo)
+                {
+                    firstRunRequest ??= requestInfo.Request;
+                }
+
+                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
+                {
+                    checkpoint = cp;
+                }
+            }
+        }
+
+        firstRunRequest.Should().NotBeNull(
+            "the ChatClientAgent + FICC pipeline should have surfaced the approval request as a workflow RequestInfoEvent");
+        checkpoint.Should().NotBeNull(
+            "a checkpoint should have been produced while the approval request was pending");
+        chatCallIndex.Should().Be(1, "the mock chat client should have been called exactly once before the approval was requested");
+        invocationCount.Should().Be(0, "the underlying tool must NOT have been invoked before the approval was granted");
+
+        ToolApprovalRequestContent? preCheckpoint = firstRunRequest!.Data.As<ToolApprovalRequestContent>();
+        preCheckpoint.Should().NotBeNull("the pending external request should carry a ToolApprovalRequestContent payload");
+        preCheckpoint!.ToolCall.Should().BeOfType<FunctionCallContent>(
+            "the pre-checkpoint pending request payload must already be a FunctionCallContent");
+
+        // Act 2 — resume from the checkpoint with a brand-new env / handle so that any
+        // in-process AIAgentHostExecutor instance state is gone and everything has to be
+        // rehydrated from the on-disk JSON.
+        ExternalRequest? resumedRequest = null;
+        List<WorkflowEvent> postResumeEvents = [];
+
+        await using (StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
+                                                     .ResumeStreamingAsync(workflow, checkpoint!))
+        {
+            using CancellationTokenSource cts = new(TimeSpan.FromSeconds(30));
+
+            // First pass: see the re-emitted RequestInfoEvent, but don't block on it.
+            await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
+            {
+                if (evt is RequestInfoEvent requestInfo)
+                {
+                    resumedRequest ??= requestInfo.Request;
+                }
+            }
+
+            resumedRequest.Should().NotBeNull(
+                "the resumed workflow should re-emit the pending approval RequestInfoEvent");
+
+            // The core issue #5350 assertion.
+            ToolApprovalRequestContent? postResume = resumedRequest!.Data.As<ToolApprovalRequestContent>();
+            postResume.Should().NotBeNull(
+                "ExternalRequest.Data.As<ToolApprovalRequestContent>() should materialize the payload after a JSON-file checkpoint resume");
+            postResume!.ToolCall.Should().NotBeNull("the resumed TARC must carry its ToolCall");
+            postResume.ToolCall.Should().BeOfType<FunctionCallContent>(
+                "after CheckpointManager.CreateJson(InMemoryJsonStore) round-trip via " +
+                "ResumeStreamingAsync, ToolApprovalRequestContent.ToolCall must still be a " +
+                "FunctionCallContent so that FunctionInvokingChatClient's pattern match " +
+                "(`tarc.ToolCall is FunctionCallContent`) continues to fire (issue #5350).");
+
+            FunctionCallContent resumedFcc = (FunctionCallContent)postResume.ToolCall;
+            resumedFcc.Name.Should().Be(ToolName);
+            resumedFcc.CallId.Should().EndWith(ToolCallId,
+                "the workflow rewrites the CallId with an executor-scoped prefix, but should preserve the original tail");
+
+            // Act 3 — send the approval response back into the resumed run and watch the
+            // remaining stream. This drives FunctionInvokingChatClient through its
+            // post-approval branch, where it must invoke the underlying AIFunction, append a
+            // FunctionResultContent, and call the model a second time.
+            ToolApprovalResponseContent approvalResponse = postResume.CreateResponse(approved: true);
+            await resumed.SendResponseAsync(resumedRequest.CreateResponse(approvalResponse));
+
+            using CancellationTokenSource cts2 = new(TimeSpan.FromSeconds(30));
+            await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts2.Token))
+            {
+                postResumeEvents.Add(evt);
+            }
+        }
+
+        // Assert 3 — the tool actually got called as part of the approval round-trip, and
+        // the workflow continued without raising errors.
+        invocationCount.Should().Be(1,
+            "approving the request should cause FunctionInvokingChatClient to invoke the wrapped AIFunction exactly once");
+        chatCallIndex.Should().Be(2,
+            "after the tool was invoked, FunctionInvokingChatClient should have made a second chat-client call to produce the final assistant message");
+        capturedInputs.Should().HaveCount(2);
+        capturedInputs[1].Should().Contain(
+            m => m.Contents.OfType<FunctionResultContent>().Any(),
+            "the second chat-client call must include the FunctionResultContent produced by the approved tool invocation");
+
+        postResumeEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
+            "no workflow errors should be raised when responding to the resumed approval request");
+        postResumeEvents.OfType<ExecutorFailedEvent>().Should().BeEmpty(
+            "no executor failures should be raised when responding to the resumed approval request");
+    }
+
+    /// <summary>
+    /// Minimal <see cref="IChatClient"/> stub for repro tests; delegates each call to a caller-supplied factory.
+    /// </summary>
+    private sealed class MockChatClient(Func<IEnumerable<ChatMessage>, ChatOptions?, ChatResponse> responseFactory) : IChatClient
+    {
+        public Task<ChatResponse> GetResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
+            => Task.FromResult(responseFactory(messages, options));
+
+        public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
+            IEnumerable<ChatMessage> messages,
+            ChatOptions? options = null,
+            [EnumeratorCancellation] CancellationToken cancellationToken = default)
+        {
+            ChatResponse response = await this.GetResponseAsync(messages, options, cancellationToken).ConfigureAwait(false);
+            foreach (ChatResponseUpdate update in response.ToChatResponseUpdates())
+            {
+                yield return update;
+            }
+        }
+
+        public object? GetService(Type serviceType, object? serviceKey = null) => null;
+        public void Dispose() { }
+    }
+
+    /// <summary>
+    /// Track A2 — same as the maximal repro (test #7) but with the agent inside a
+    /// <c>GroupChatBuilder</c> (round-robin manager with a single participant), to rule out
+    /// a group-chat-specific re-wrap or replay path that drops the
+    /// <see cref="ToolApprovalRequestContent.ToolCall"/> type during the checkpoint round-trip.
+    ///
+    /// <para><b>Finding:</b> the <see cref="FunctionCallContent"/> type IS preserved after
+    /// resume (consistent with tests #1 – #7 — the OP's hypothesis still does not reproduce
+    /// in this configuration). However, sending an approval response back into the resumed
+    /// group-chat workflow surfaces a <i>different</i>, real bug:
+    /// <c>FunctionInvokingChatClient.ExtractAndRemoveApprovalRequestsAndResponses</c> throws
+    /// <see cref="ArgumentException"/> with message
+    /// <c>"An item with the same key has already been added. Key: ficc_call-1"</c>.
+    /// This test pins that observed behavior so future investigation can latch onto it.</para>
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_A2_GroupChatBuilder_WithApprovalRequiredTool_JsonCheckpointResume_PreservesFunctionCallContentAsync()
+    {
+        ReproHarness harness = new();
+        Workflow workflow = AgentWorkflowBuilder
+            .CreateGroupChatBuilderWith(agents => new RoundRobinGroupChatManager(agents) { MaximumIterationCount = 4 })
+            .AddParticipants(harness.Agent)
+            .Build();
+
+        await RunReproAsync(
+            workflow,
+            harness,
+            CheckpointManager.CreateJson(new InMemoryJsonStore()),
+            scenarioName: "A2 (group chat)",
+            expectCleanPostApprovalCompletion: false,
+            postApprovalCompletionAssertion: events =>
+            {
+                // A2 currently surfaces a duplicate-key crash inside FICC when the group-chat
+                // workflow resumes with a pending approval request and the response arrives.
+                // This assertion pins the observed misbehavior. If the upstream
+                // GroupChat + AIAgentHostExecutor + FICC interaction is fixed, this test will
+                // start failing here — that's intentional. The fix should then either remove
+                // this assertion or convert it to a clean-completion assertion mirroring
+                // test #7. TODO(#5350-followup): file a separate issue for the duplicate-key
+                // crash if one does not already exist, and link it here.
+                ArgumentException? duplicateKey = events
+                    .OfType<WorkflowErrorEvent>()
+                    .Select(e => e.Data as Exception)
+                    .Select(e => e?.InnerException as ArgumentException ?? e as ArgumentException)
+                    .FirstOrDefault(e => e?.Message.Contains("ficc_call-1", StringComparison.Ordinal) == true);
+                duplicateKey.Should().NotBeNull(
+                    "[A2 (group chat)] approving the resumed approval request currently surfaces a duplicate-key " +
+                    "ArgumentException out of FunctionInvokingChatClient.ExtractAndRemoveApprovalRequestsAndResponses — " +
+                    "this is a real bug, but it is NOT the bug claimed in issue #5350. The TARC.ToolCall was already " +
+                    "asserted to be a FunctionCallContent above; the OP's hypothesis remains unreproduced.");
+            });
+    }
+
+    /// <summary>
+    /// Track A2b — same as A2, but using a <c>HandoffWorkflowBuilder</c> instead of a group
+    /// chat. The initial agent is the same approval-tool-equipped <see cref="ChatClientAgent"/>
+    /// as test #7; a second dummy agent is registered solely so the handoff graph has a valid
+    /// peer (the mock chat client never emits a <c>handoff_to_*</c> call, so the workflow stays
+    /// on the initial agent). This isolates whether anything in the handoff-specific
+    /// orchestration (handoff tool injection, <c>HandoffMessagesFilter</c>, the
+    /// <c>HandoffStartExecutor</c>/<c>HandoffEndExecutor</c> wrap-up) perturbs the
+    /// <see cref="ToolApprovalRequestContent"/> payload across a JSON checkpoint resume.
+    ///
+    /// <para><b>Finding:</b> the handoff path is fully clean. The <see cref="FunctionCallContent"/>
+    /// type is preserved after resume <i>and</i> approving the resumed request completes the
+    /// workflow without errors and invokes the wrapped <see cref="AIFunction"/> exactly once.
+    /// This is in contrast to A2 (group chat), which preserves the type but crashes on
+    /// approval with a duplicate-key <see cref="ArgumentException"/> in FICC. The OP's
+    /// hypothesis (<c>TARC.ToolCall is not FunctionCallContent</c>) still does not reproduce.
+    /// </para>
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_A2b_HandoffWorkflowBuilder_WithApprovalRequiredTool_JsonCheckpointResume_PreservesFunctionCallContentAndInvokesToolAsync()
+    {
+        ReproHarness harness = new();
+
+        // Second agent is a no-op peer required to give the handoff graph a valid target.
+        // The mock chat client only ever emits a FunctionCallContent for GetWeather, so the
+        // initial agent never actually hands off; the second agent is never invoked.
+        MockChatClient peerChatClient = new((messages, options) =>
+            new ChatResponse(new ChatMessage(ChatRole.Assistant, "(unused peer)")));
+        ChatClientAgent peerAgent = new(
+            peerChatClient,
+            instructions: "Unused peer agent.",
+            name: "PeerAgent");
+
+        Workflow workflow = AgentWorkflowBuilder
+            .CreateHandoffBuilderWith(harness.Agent)
+            .WithHandoff(harness.Agent, peerAgent)
+            .Build();
+
+        await RunReproAsync(
+            workflow,
+            harness,
+            CheckpointManager.CreateJson(new InMemoryJsonStore()),
+            scenarioName: "A2b (handoff)");
+    }
+
+    /// <summary>
+    /// Track A3 — same as the maximal repro (test #7) but the checkpoint <see cref="JsonElement"/>
+    /// is round-tripped through <see cref="JsonElement.GetRawText"/> + <see cref="JsonDocument.Parse(string,JsonDocumentOptions)"/>
+    /// between commit and retrieve, to emulate the SQL <c>nvarchar</c> / Dapper hop in the
+    /// OP's setup. This catches cases where the storage layer would only fail if it perturbed
+    /// the JSON in some way (e.g. dropped metadata, re-encoded numbers), and confirms a
+    /// byte-preserving string round-trip on its own is harmless.
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_A3_StringRoundTripStore_PreservesFunctionCallContentAsync()
+    {
+        ReproHarness harness = new();
+        Workflow workflow = new WorkflowBuilder(harness.Agent).Build();
+
+        CheckpointManager checkpointManager = CheckpointManager.CreateJson(
+            new StringRoundTripJsonStore(new InMemoryJsonStore()));
+
+        await RunReproAsync(
+            workflow,
+            harness,
+            checkpointManager,
+            scenarioName: "A3 (string round-trip store)");
+    }
+
+    /// <summary>
+    /// Track A4 — same as the maximal repro (test #7) but with a non-default
+    /// <see cref="JsonSerializerOptions"/> passed as <c>customOptions</c> to
+    /// <see cref="CheckpointManager.CreateJson"/>. The custom options intentionally do NOT
+    /// include the polymorphism resolver chain (<c>AgentAbstractionsJsonUtilities</c> →
+    /// <c>AIJsonUtilities</c>) — confirming that <c>JsonMarshaller</c>'s internal
+    /// <c>WorkflowsJsonUtilities.DefaultOptions</c> chain always wins for known
+    /// <see cref="AIContent"/> types and the external options cannot silently displace it.
+    /// </summary>
+    [Fact]
+    public async Task Repro_5350_A4_CustomJsonSerializerOptions_PreservesFunctionCallContentAsync()
+    {
+        ReproHarness harness = new();
+        Workflow workflow = new WorkflowBuilder(harness.Agent).Build();
+
+        // Custom options that DO NOT know about AIContent / FunctionCallContent.
+        JsonSerializerOptions customOptions = new(JsonSerializerDefaults.Web)
+        {
+            WriteIndented = true,
+        };
+
+        CheckpointManager checkpointManager = CheckpointManager.CreateJson(
+            new InMemoryJsonStore(),
+            customOptions);
+
+        await RunReproAsync(
+            workflow,
+            harness,
+            checkpointManager,
+            scenarioName: "A4 (custom JsonSerializerOptions)");
+    }
+
+    /// <summary>
+    /// Shared end-to-end repro driver used by tests #7, A2, A3, A4.
+    /// Drives the workflow until an approval request appears, captures the latest checkpoint,
+    /// disposes the run, resumes from the checkpoint, and asserts that the resumed
+    /// <see cref="RequestInfoEvent"/>'s <see cref="ToolApprovalRequestContent.ToolCall"/> is
+    /// still a <see cref="FunctionCallContent"/>. Then sends an approval response and asserts
+    /// the wrapped <see cref="AIFunction"/> is invoked exactly once.
+    /// </summary>
+    private static async Task RunReproAsync(
+        Workflow workflow,
+        ReproHarness harness,
+        CheckpointManager checkpointManager,
+        string scenarioName,
+        bool expectCleanPostApprovalCompletion = true,
+        Action<IReadOnlyList<WorkflowEvent>>? postApprovalCompletionAssertion = null)
+    {
+        InProcessExecutionEnvironment env = InProcessExecution.OffThread;
+        List<ChatMessage> inputMessages = [new(ChatRole.User, "What's the weather in Amsterdam?")];
+
+        // Act 1 — run until approval request appears and capture latest checkpoint.
+        ExternalRequest? firstRunRequest = null;
+        CheckpointInfo? checkpoint = null;
+
+        await using (StreamingRun firstRun = await env.WithCheckpointing(checkpointManager)
+                                                      .RunStreamingAsync(workflow, inputMessages))
+        {
+            (await firstRun.TrySendMessageAsync(new TurnToken(emitEvents: false)))
+                .Should().BeTrue($"[{scenarioName}] the workflow should accept a TurnToken");
+
+            using CancellationTokenSource cts = new(TimeSpan.FromSeconds(30));
+            await foreach (WorkflowEvent evt in firstRun.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
+            {
+                if (evt is RequestInfoEvent requestInfo)
+                {
+                    firstRunRequest ??= requestInfo.Request;
+                }
+
+                if (evt is SuperStepCompletedEvent step && step.CompletionInfo?.Checkpoint is { } cp)
+                {
+                    checkpoint = cp;
+                }
+            }
+        }
+
+        firstRunRequest.Should().NotBeNull(
+            $"[{scenarioName}] the ChatClientAgent + FICC pipeline should surface the approval request as a workflow RequestInfoEvent");
+        checkpoint.Should().NotBeNull(
+            $"[{scenarioName}] a checkpoint should have been produced while the approval request was pending");
+        harness.ChatCallCount.Should().Be(1, $"[{scenarioName}] the mock chat client should have been called exactly once before approval was requested");
+        harness.InvocationCount.Should().Be(0, $"[{scenarioName}] the underlying tool must NOT have been invoked before approval was granted");
+
+        ToolApprovalRequestContent? preCheckpoint = firstRunRequest!.Data.As<ToolApprovalRequestContent>();
+        preCheckpoint.Should().NotBeNull($"[{scenarioName}] the pending external request should carry a ToolApprovalRequestContent payload");
+        preCheckpoint!.ToolCall.Should().BeOfType<FunctionCallContent>(
+            $"[{scenarioName}] the pre-checkpoint pending request payload must already be a FunctionCallContent");
+
+        // Act 2 — resume from checkpoint on a fresh handle.
+        ExternalRequest? resumedRequest = null;
+        List<WorkflowEvent> postResumeEvents = [];
+
+        await using (StreamingRun resumed = await env.WithCheckpointing(checkpointManager)
+                                                     .ResumeStreamingAsync(workflow, checkpoint!))
+        {
+            using CancellationTokenSource cts = new(TimeSpan.FromSeconds(30));
+            await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts.Token))
+            {
+                if (evt is RequestInfoEvent requestInfo)
+                {
+                    resumedRequest ??= requestInfo.Request;
+                }
+            }
+
+            resumedRequest.Should().NotBeNull(
+                $"[{scenarioName}] the resumed workflow should re-emit the pending approval RequestInfoEvent");
+
+            ToolApprovalRequestContent? postResume = resumedRequest!.Data.As<ToolApprovalRequestContent>();
+            postResume.Should().NotBeNull(
+                $"[{scenarioName}] ExternalRequest.Data.As<ToolApprovalRequestContent>() should materialize the payload after JSON-checkpoint resume");
+            postResume!.ToolCall.Should().NotBeNull($"[{scenarioName}] the resumed TARC must carry its ToolCall");
+            postResume.ToolCall.Should().BeOfType<FunctionCallContent>(
+                $"[{scenarioName}] after CheckpointManager.CreateJson round-trip via ResumeStreamingAsync, " +
+                "ToolApprovalRequestContent.ToolCall must still be a FunctionCallContent so that " +
+                "FunctionInvokingChatClient's pattern match (`tarc.ToolCall is FunctionCallContent`) continues to fire (issue #5350).");
+
+            // Act 3 — approve and finish the workflow.
+            ToolApprovalResponseContent approvalResponse = postResume.CreateResponse(approved: true);
+            await resumed.SendResponseAsync(resumedRequest.CreateResponse(approvalResponse));
+
+            using CancellationTokenSource cts2 = new(TimeSpan.FromSeconds(30));
+            await foreach (WorkflowEvent evt in resumed.WatchStreamAsync(blockOnPendingRequest: false, cts2.Token))
+            {
+                postResumeEvents.Add(evt);
+            }
+        }
+
+        if (expectCleanPostApprovalCompletion)
+        {
+            harness.InvocationCount.Should().Be(1,
+                $"[{scenarioName}] approving the request should cause FunctionInvokingChatClient to invoke the wrapped AIFunction exactly once");
+            postResumeEvents.OfType<WorkflowErrorEvent>().Should().BeEmpty(
+                $"[{scenarioName}] no workflow errors should be raised when responding to the resumed approval request");
+            postResumeEvents.OfType<ExecutorFailedEvent>().Should().BeEmpty(
+                $"[{scenarioName}] no executor failures should be raised when responding to the resumed approval request");
+        }
+
+        postApprovalCompletionAssertion?.Invoke(postResumeEvents);
+    }
+
+    /// <summary>
+    /// Bundles a <see cref="ChatClientAgent"/> + counting <see cref="ApprovalRequiredAIFunction"/>
+    /// + <see cref="MockChatClient"/> in a single reusable harness so the four end-to-end repro
+    /// variants (#7, A2, A3, A4) can share identical setup.
+    /// </summary>
+    private sealed class ReproHarness
+    {
+        public const string ToolName = "GetWeather";
+        public const string ToolResultText = "Sunny, 22°C";
+        public const string ToolCallId = "call-1";
+        public const string FinalAssistantText = "The weather in Amsterdam is sunny and 22°C.";
+
+        private int _invocationCount;
+        private int _chatCallIndex;
+
+        public int InvocationCount => Volatile.Read(ref this._invocationCount);
+        public int ChatCallCount => Volatile.Read(ref this._chatCallIndex);
+
+        public ChatClientAgent Agent { get; }
+
+        public ReproHarness()
+        {
+            AIFunction underlyingTool = AIFunctionFactory.Create(
+                ([Description("City to look up")] string city) =>
+                {
+                    Interlocked.Increment(ref this._invocationCount);
+                    return ToolResultText;
+                },
+                name: ToolName,
+                description: "Gets the weather for the given city");
+
+            ApprovalRequiredAIFunction approvalTool = new(underlyingTool);
+
+            MockChatClient mockChatClient = new((messages, options) =>
+            {
+                int index = Interlocked.Increment(ref this._chatCallIndex) - 1;
+                return index switch
+                {
+                    0 => new ChatResponse(new ChatMessage(ChatRole.Assistant,
+                        [new FunctionCallContent(
+                            callId: ToolCallId,
+                            name: ToolName,
+                            arguments: new Dictionary<string, object?> { ["city"] = "Amsterdam" })])),
+                    _ => new ChatResponse(new ChatMessage(ChatRole.Assistant, FinalAssistantText)),
+                };
+            });
+
+            this.Agent = new ChatClientAgent(
+                mockChatClient,
+                instructions: "You are a weather agent.",
+                name: "WeatherAgent",
+                tools: [approvalTool]);
+        }
+    }
+
+    /// <summary>
+    /// Wraps a <see cref="JsonCheckpointStore"/> and forces every <see cref="JsonElement"/> to
+    /// round-trip through <c>GetRawText()</c> + <see cref="JsonDocument.Parse(string,JsonDocumentOptions)"/>
+    /// during commit and again during retrieve. This emulates a Dapper-backed SQL store where
+    /// the <see cref="JsonElement"/> is materialized to a string for the <c>nvarchar(max)</c>
+    /// column on the way in and re-parsed on the way back out. Used by the A3 test only;
+    /// the double parse-and-clone is intentionally extra work and not suitable for production use.
+    /// </summary>
+    private sealed class StringRoundTripJsonStore(JsonCheckpointStore inner) : JsonCheckpointStore
+    {
+        public override async ValueTask<CheckpointInfo> CreateCheckpointAsync(string sessionId, JsonElement value, CheckpointInfo? parent = null)
+        {
+            JsonElement roundTripped = RoundTrip(value);
+            return await inner.CreateCheckpointAsync(sessionId, roundTripped, parent).ConfigureAwait(false);
+        }
+
+        public override async ValueTask<JsonElement> RetrieveCheckpointAsync(string sessionId, CheckpointInfo key)
+        {
+            JsonElement raw = await inner.RetrieveCheckpointAsync(sessionId, key).ConfigureAwait(false);
+            return RoundTrip(raw);
+        }
+
+        public override ValueTask<IEnumerable<CheckpointInfo>> RetrieveIndexAsync(string sessionId, CheckpointInfo? withParent = null)
+            => inner.RetrieveIndexAsync(sessionId, withParent);
+
+        private static JsonElement RoundTrip(JsonElement element)
+        {
+            string raw = element.GetRawText();
+            using JsonDocument doc = JsonDocument.Parse(raw);
+            return doc.RootElement.Clone();
+        }
+    }
+}

python/CHANGELOG.md

@@ -7,23 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [1.5.0] - 2026-05-19
-
-### Added
-- **agent-framework-core**, **agent-framework-foundry**, **agent-framework-openai**: Record actual served model from Azure OpenAI ([#5910](https://github.com/microsoft/agent-framework/pull/5910))
-- **samples**: New Foundry Hosted Agents samples for RAG, Skills, and Memory ([#5822](https://github.com/microsoft/agent-framework/pull/5822))
-
-### Changed
-- **agent-framework-core**, **agent-framework-azurefunctions**, **agent-framework-devui**, **agent-framework-foundry**, **agent-framework-orchestrations**: Improve handling of intermediate outputs for workflows and orchestrations ([#5623](https://github.com/microsoft/agent-framework/pull/5623))
-- **agent-framework-durabletask**: Pin `durabletask` and `durabletask-azuremanaged` floors to `>=1.4.0` and exclude upstream `durabletask` 1.4.1, 1.4.2, and 1.4.3 from the supported version range.
-- **agent-framework-orchestrations**: Bumped package to release candidate stage.
-
-### Fixed
-- **agent-framework-core**: Parse YAML block scalars in SKILL.md frontmatter ([#5863](https://github.com/microsoft/agent-framework/pull/5863))
-- **agent-framework-github-copilot**: Include tools added by `ContextProvider.before_run` in session creation ([#5780](https://github.com/microsoft/agent-framework/pull/5780))
-- **agent-framework-hyperlight**: Skip symlinks when staging sandbox input ([#5919](https://github.com/microsoft/agent-framework/pull/5919))
-- **agent-framework-purview**: Remove duplicate pop in `InMemoryCacheProvider.remove` ([#5795](https://github.com/microsoft/agent-framework/pull/5795))
-
 ## [1.4.0] - 2026-05-14
 
 ### Added
@@ -1088,8 +1071,7 @@ Release candidate for **agent-framework-core** and **agent-framework-azure-ai**
 
 For more information, see the [announcement blog post](https://devblogs.microsoft.com/foundry/introducing-microsoft-agent-framework-the-open-source-engine-for-agentic-ai-apps/).
 
-[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.5.0...HEAD
-[1.5.0]: https://github.com/microsoft/agent-framework/compare/python-1.4.0...python-1.5.0
+[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.4.0...HEAD
 [1.4.0]: https://github.com/microsoft/agent-framework/compare/python-1.3.0...python-1.4.0
 [1.3.0]: https://github.com/microsoft/agent-framework/compare/python-1.2.2...python-1.3.0
 [1.2.2]: https://github.com/microsoft/agent-framework/compare/python-1.2.1...python-1.2.2

python/packages/a2a/pyproject.toml

@@ -4,7 +4,7 @@ description = "A2A integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "a2a-sdk>=1.0.0,<2",
 ]
 

python/packages/ag-ui/pyproject.toml

@@ -22,10 +22,10 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "ag-ui-protocol>=0.1.16,<0.2",
     "fastapi>=0.115.0,<0.133.1",
-    "uvicorn[standard]>=0.30.0,<1"
+    "uvicorn[standard]>=0.30.0,<0.42.0"
 ]
 
 [project.optional-dependencies]

python/packages/anthropic/pyproject.toml

@@ -4,7 +4,7 @@ description = "Anthropic integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "anthropic>=0.80.0,<0.80.1",
 ]
 

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

@@ -4,7 +4,7 @@ description = "Azure AI Search integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "azure-search-documents>=11.7.0b2,<11.7.0b3",
 ]
 

python/packages/azure-contentunderstanding/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure Content Understanding integration for Microsoft Agent Frame
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com" }]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260519"
+version = "1.0.0a260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,8 +23,8 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
-    "agent-framework-foundry>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
+    "agent-framework-foundry>=1.4.0,<2",
     "azure-ai-contentunderstanding>=1.0.1,<1.1",
     "aiohttp>=3.9,<4",
     "filetype>=1.2,<2",

python/packages/azure-cosmos/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure Cosmos DB history provider integration for Microsoft Agent
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "azure-cosmos>=4.3.0,<5",
 ]
 

python/packages/azurefunctions/pyproject.toml

@@ -4,7 +4,7 @@ description = "Azure Functions integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,8 +22,8 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
-    "agent-framework-durabletask>=1.0.0b260519,<2",
+    "agent-framework-core>=1.4.0,<2",
+    "agent-framework-durabletask",
     "azure-functions>=1.24.0,<2",
     "azure-functions-durable>=1.3.1,<2",
 ]

python/packages/bedrock/pyproject.toml

@@ -4,7 +4,7 @@ description = "Amazon Bedrock integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "boto3>=1.35.0,<2.0.0",
     "botocore>=1.35.0,<2.0.0",
 ]

python/packages/chatkit/pyproject.toml

@@ -4,7 +4,7 @@ description = "OpenAI ChatKit integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "openai-chatkit>=1.4.1,<2.0.0",
 ]
 

python/packages/claude/pyproject.toml

@@ -4,7 +4,7 @@ description = "Claude Agent SDK integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "claude-agent-sdk>=0.1.36,<0.1.49",
 ]
 

python/packages/copilotstudio/pyproject.toml

@@ -4,7 +4,7 @@ description = "Copilot Studio integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "microsoft-agents-copilotstudio-client>=0.3.1,<0.3.2",
 ]
 

python/packages/core/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.5.0"
+version = "1.4.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"

python/packages/declarative/pyproject.toml

@@ -4,7 +4,7 @@ description = "Declarative specification support for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "httpx>=0.27,<1",
     "powerfx>=0.0.32,<0.0.35; python_version < '3.14'",
     "pyyaml>=6.0,<7.0",

python/packages/devui/pyproject.toml

@@ -4,7 +4,7 @@ description = "Debug UI for Microsoft Agent Framework with OpenAI-compatible API
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,18 +23,18 @@ classifiers = [
   "Typing :: Typed",
 ]
  dependencies = [
-     "agent-framework-core>=1.5.0,<2",
+     "agent-framework-core>=1.4.0,<2",
      "openai>=1.99.0,<3",
      "opentelemetry-sdk>=1.39.0,<2",
      "fastapi>=0.115.0,<0.133.1",
-     "uvicorn[standard]>=0.30.0,<1"
+     "uvicorn[standard]>=0.30.0,<0.42.0"
  ]
 
 [project.optional-dependencies]
 dev = [
     "pytest==9.0.3",
     "watchdog==6.0.0",
-    "agent-framework-orchestrations==1.0.0rc1",
+    "agent-framework-orchestrations==1.0.0b260402",
 ]
 all = [
     "pytest==9.0.3",

python/packages/durabletask/pyproject.toml

@@ -4,7 +4,7 @@ description = "Durable Task integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,9 +22,9 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
-    "durabletask>=1.4.0,!=1.4.1,!=1.4.2,!=1.4.3,<2",
-    "durabletask-azuremanaged>=1.4.0,<2",
+    "agent-framework-core>=1.4.0,<2",
+    "durabletask>=1.3.0,<2",
+    "durabletask-azuremanaged>=1.3.0,<2",
     "python-dateutil>=2.8.0,<3",
 ]
 

python/packages/foundry/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Foundry integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.5.0"
+version = "1.4.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,8 +23,8 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
-    "agent-framework-openai>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
+    "agent-framework-openai>=1.4.0,<2",
     "azure-ai-inference>=1.0.0b9,<1.0.0b10",
     "azure-ai-projects>=2.1.0,<3.0",
 ]

python/packages/foundry_hosting/pyproject.toml

@@ -4,7 +4,7 @@ description = "Foundry Hosting integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260519"
+version = "1.0.0a260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "azure-ai-agentserver-core>=2.0.0b3,<3",
     "azure-ai-agentserver-responses>=1.0.0b5,<2",
     "azure-ai-agentserver-invocations>=1.0.0b3,<2",

python/packages/foundry_local/pyproject.toml

@@ -4,7 +4,7 @@ description = "Foundry Local integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,8 +23,8 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
-    "agent-framework-openai>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
+    "agent-framework-openai>=1.4.0,<2",
     "foundry-local-sdk>=0.5.1,<0.5.2",
 ]
 

python/packages/gemini/pyproject.toml

@@ -4,7 +4,7 @@ description = "Google Gemini integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260519"
+version = "1.0.0a260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2.0",
+    "agent-framework-core>=1.4.0,<2.0",
     "google-genai>=1.65.0,<2.0.0",
 ]
 

python/packages/github_copilot/pyproject.toml

@@ -4,7 +4,7 @@ description = "GitHub Copilot integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "github-copilot-sdk>=1.0.0b2,<=1.0.0b2; python_version >= '3.11'",
 ]
 

python/packages/hyperlight/pyproject.toml

@@ -4,7 +4,7 @@ description = "Hyperlight CodeAct integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "hyperlight-sandbox>=0.4.0,<0.5",
     "hyperlight-sandbox-backend-wasm>=0.4.0,<0.5 ; ((sys_platform == 'linux' and platform_machine == 'x86_64') or (sys_platform == 'win32' and platform_machine == 'AMD64')) and python_version < '3.14'",
     "hyperlight-sandbox-python-guest>=0.4.0,<0.5",

python/packages/lab/pyproject.toml

@@ -4,7 +4,7 @@ description = "Experimental modules for Microsoft Agent Framework"
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
   "Programming Language :: Python :: 3.14",
 ]
 dependencies = [
-  "agent-framework-core>=1.5.0,<2",
+  "agent-framework-core>=1.4.0,<2",
 ]
 
 [project.optional-dependencies]

python/packages/mem0/pyproject.toml

@@ -4,7 +4,7 @@ description = "Mem0 integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "mem0ai>=1.0.0,<2",
 ]
 

python/packages/ollama/pyproject.toml

@@ -4,7 +4,7 @@ description = "Ollama integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://learn.microsoft.com/en-us/agent-framework/"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "ollama>=0.5.3,<0.5.4",
 ]
 

python/packages/openai/pyproject.toml

@@ -4,7 +4,7 @@ description = "OpenAI integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.5.0"
+version = "1.4.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "openai>=1.99.0,<3",
 ]
 

python/packages/orchestrations/pyproject.toml

@@ -4,7 +4,7 @@ description = "Orchestration patterns for Microsoft Agent Framework. Includes Se
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0rc1"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
 ]
 
 [tool.uv]

python/packages/purview/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Purview (Graph dataSecurityAndGovernance) integration f
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "azure-core>=1.30.0,<2",
     "httpx>=0.27.0,<0.29",
 ]

python/packages/redis/pyproject.toml

@@ -4,7 +4,7 @@ description = "Redis integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260519"
+version = "1.0.0b260514"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.5.0,<2",
+    "agent-framework-core>=1.4.0,<2",
     "redis>=6.4.0,<7.2.1",
     "redisvl>=0.11.0,<0.16",
     "numpy>=2.2.6,<3"

python/pyproject.toml

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.5.0"
+version = "1.4.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
   "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core[all]==1.5.0",
+    "agent-framework-core[all]==1.4.0",
 ]
 
 [dependency-groups]