.NET: Allow Simulating service stored ChatHistory to improve consistency (#4974)

* Allow Simulating service stored ChatHistory to improve consistency

* Fixing bug in ServiceStoredSimulatingChatClient

* Addressing PR comments.

* Address PR comments

* Apply suggestion from @SergeyMenshykh

Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com>

* Fix bug

---------

Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com>
This commit is contained in:
westey
2026-03-30 18:52:01 +00:00
committed by GitHub
co-authored by SergeyMenshykh
parent 18f7ba8632
commit 401e5dc7e8
16 changed files with 950 additions and 714 deletions
@@ -1,15 +1,16 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how the ChatClientAgent persists chat history after each individual
// call to the AI service.
// call to the AI service, using the SimulateServiceStoredChatHistory option.
// When an agent uses tools, FunctionInvokingChatClient may loop multiple times
// (service call → tool execution → service call), and intermediate messages (tool calls and
// results) are persisted after each service call. This allows you to inspect or recover them
// even if the process is interrupted mid-loop, but may also result in chat history that is not
// yet finalized (e.g., tool calls without results) being persisted, which may be undesirable in some cases.
//
// To opt into end-of-run persistence instead (atomic run semantics), set
// PersistChatHistoryAtEndOfRun = true on ChatClientAgentOptions.
// To use end-of-run persistence instead (atomic run semantics), remove the
// SimulateServiceStoredChatHistory = true setting (or set it to false). End-of-run
// persistence is the default behavior.
//
// The sample runs two multi-turn conversations: one using non-streaming (RunAsync) and one
// using streaming (RunStreamingAsync), to demonstrate correct behavior in both modes.
@@ -53,7 +54,7 @@ static string GetTime([Description("The city name.")] string city) =>
_ => $"{city}: time data not available."
};
// Create the agent — per-service-call persistence is the default behavior.
// Create the agent — per-service-call persistence is enabled via SimulateServiceStoredChatHistory.
// The in-memory ChatHistoryProvider is used by default when the service does not require service stored chat
// history, so for those cases, we can inspect the chat history via session.TryGetInMemoryChatHistory().
IChatClient chatClient = string.Equals(store, "TRUE", StringComparison.OrdinalIgnoreCase) ?
@@ -63,6 +64,7 @@ AIAgent agent = chatClient.AsAIAgent(
new ChatClientAgentOptions
{
Name = "WeatherAssistant",
SimulateServiceStoredChatHistory = true,
ChatOptions = new()
{
Instructions = "You are a helpful assistant. When asked about multiple cities, call the appropriate tool for each city.",
@@ -1,16 +1,19 @@
# In-Function-Loop Checkpointing
This sample demonstrates how `ChatClientAgent` persists chat history after each individual call to the AI service by default. This per-service-call persistence ensures intermediate progress is saved during the function invocation loop.
This sample demonstrates how `ChatClientAgent` can persist chat history after each individual call to the AI service using the `SimulateServiceStoredChatHistory` option. This per-service-call persistence ensures intermediate progress is saved during the function invocation loop.
## What This Sample Shows
When an agent uses tools, the `FunctionInvokingChatClient` loops multiple times (service call → tool execution → service call → …). By default, chat history is persisted after each service call via the `ChatHistoryPersistingChatClient` decorator:
When an agent uses tools, the `FunctionInvokingChatClient` loops multiple times (service call → tool execution → service call → …). By enabling `SimulateServiceStoredChatHistory = true`, chat history is persisted after each service call via the `ServiceStoredSimulatingChatClient` decorator:
- A `ChatHistoryPersistingChatClient` decorator is automatically inserted into the chat client pipeline
- A `ServiceStoredSimulatingChatClient` decorator is inserted into the chat client pipeline
- Before each service call, the decorator loads history from the `ChatHistoryProvider` and prepends it to the request
- After each service call, the decorator notifies the `ChatHistoryProvider` (and any `AIContextProvider` instances) with the new messages
- Only **new** messages are sent to providers on each notification — messages that were already persisted in an earlier call within the same run are deduplicated automatically
To opt into end-of-run persistence instead (atomic run semantics), set `PersistChatHistoryAtEndOfRun = true` on `ChatClientAgentOptions`. In that mode, the decorator marks messages with metadata rather than persisting them immediately, and `ChatClientAgent` persists only the marked messages at the end of the run.
By default (without `SimulateServiceStoredChatHistory`), chat history is persisted at the end of the full agent run instead. To use per-service-call persistence, set `SimulateServiceStoredChatHistory = true` on `ChatClientAgentOptions`.
With `SimulateServiceStoredChatHistory` = true, the behavior matches that of chat history stored in the underlying AI service exactly.
Per-service-call persistence is useful for:
- **Crash recovery** — if the process is interrupted mid-loop, the intermediate tool calls and results are already persisted
@@ -26,7 +29,7 @@ The sample asks the agent about the weather and time in three cities. The model
```
ChatClientAgent
└─ FunctionInvokingChatClient (handles tool call loop)
└─ ChatHistoryPersistingChatClient (persists after each service call)
└─ ServiceStoredSimulatingChatClient (persists after each service call)
└─ Leaf IChatClient (Azure OpenAI)
```