mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
5ac864dfd9287186bcd91f3d8f777d5319886ccd
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
b559545fa4 |
.NET: Fix declarative workflow regressions for hosted agents (#5905)
* Fix declarative workflow regressions for hosted agents
Three regressions surfaced when running a declarative workflow as a
Foundry hosted agent. Together they caused every condition group to fall
through to elseActions and the raw agent JSON to leak to the caller.
1. AgentProviderExtensions.InvokeAgentAsync forced autoSend to true
whenever the agent ran on the workflow conversation, which overrode
the explicit autoSend: false declared in workflow.yaml and streamed
the raw structured-output JSON straight to the user. Honor the
caller-supplied autoSend instead.
2. IWorkflowContextExtensions.ReadState / QueueStateUpdateAsync /
QueueStateResetAsync took the variable name and namespace alias
directly from PropertyPath.VariableName / NamespaceAlias. Against
Microsoft.Agents.ObjectModel 2026.2.4.1 those properties return null
for a dotted reference such as `Local.Triage` even when
SegmentCount == 2 and IsValid == true, so every assignment threw
ArgumentNullException via Throw.IfNull. Fall back to Segments() to
reconstruct the name and alias when the parser returns null.
3. The same ObjectModel version no longer recognizes the user-facing
`Local` scope alias: VariableScopeNames.IsValidName(`Local`)
returns false and GetNamespaceFromName(`Local`) returns Unknown, so
the declarative interpreter's IsManagedScope check fails and the
State.Set call is silently skipped. Translate the `Local` alias to
its canonical `Topic` form before forwarding to
QueueStateUpdateAsync; WorkflowFormulaState.Bind continues to expose
it as `Local` to PowerFx.
Verified end-to-end against a deployed Foundry hosted agent: the
declarative triage workflow now routes Technical / Billing / General
inputs correctly and only the autoSend-eligible messages reach the
caller.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Hosted-agent HITL: persist session across previous_response_id chains; run approved local AIFunctions
Two regressions hit declarative workflows that use require_approval=true when
the client chains turns via previous_response_id (no conversation_id):
1. AgentFrameworkResponseHandler keyed the AgentSession store solely on
conversation_id, so when only previous_response_id was present the
StateBag (which holds ToolApprovalIdMap) was discarded after each turn.
The next turn then threw 'No approval mapping recorded for wire id ...'
in InputConverter.ConvertMcpApprovalResponse.
Fix: fall back to previous_response_id on load and to context.ResponseId
on save so the response-id chain becomes a valid session key. Conversation
id remains preferred when present.
2. InvokeFunctionToolExecutor.CaptureResponseAsync only acted on
FunctionResultContent. In the hosted Foundry path the approval response
arrives as a ToolApprovalResponseContent with no FunctionResultContent,
so the local AIFunction never ran and downstream PropertyPath/SendActivity
consumers (e.g. {Local.RefundResult}) saw empty values.
Fix: when no FunctionResultContent matches but an approved
ToolApprovalResponseContent does, look up the registered AIFunction by
name on agentProvider.Functions and invoke it with the evaluated
arguments, surfacing the result through the existing assignment path.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Apply PropertyPath workaround to initialization path; share + tidy helpers
Address PR #5905 review feedback:
* Move the PropertyPath VariableName/NamespaceAlias fallback and 'Local'
-> 'Topic' scope remap into a shared internal PropertyPathExtensions
helper. Materializes Segments() once, names the magic 'Local' alias
as a const, and carries a TODO referencing the tracking issue.
* Apply the same helper in WorkflowDiagnostics.InitializeDefaults so a
declared default for a dotted variable like 'Local.Triage' is no
longer silently skipped at workflow startup (closes the gap flagged
by the reviewer: runtime ReadState/QueueStateUpdateAsync worked but
state.Initialize did not).
* Restore the previous strict failure mode on namespace alias by
wrapping GetNamespaceAlias() in Throw.IfNull at call sites so a
malformed single-segment path keeps failing fast rather than
silently passing null to State.Get/Set.
All 821 unit tests pass.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add tests for AgentProviderExtensions.InvokeAgentAsync autoSend behavior
Covers the autoSend regression fix: when the agent runs on the workflow conversation with autoSend=false, no AgentResponseUpdateEvent or AgentResponseEvent is added to the context. Also covers autoSend=true (events emitted) and autoSend=false on a non-workflow conversation.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Surface SendActivity output via AgentResponseUpdateEvent
SendActivityExecutor previously only emitted the activity text via YieldOutputAsync, which the runtime converts to an AgentResponseEvent. WorkflowSession gates AgentResponseEvent behind includeWorkflowOutputsInResponse, so when a host opts out of summary outputs (the default for AsAIAgent) the SendActivity reply is silently dropped.
Mirror the pattern used by AgentProviderExtensions for autoSend agent invocations: also emit an AgentResponseUpdateEvent, which WorkflowSession yields unconditionally. This makes SendActivity reliably reach chat-protocol clients without requiring includeWorkflowOutputsInResponse = true (which would also duplicate autoSend agent output).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Revert previous_response_id session-key fallback
The fallback let a session be keyed by an unbroken previous_response_id chain,
but conversation_id is the right way to thread state across turns: it survives
shared/branched chains (e.g. when another agent generates a response in between)
and is the documented model for stateful clients. Restore conversation_id as the
sole session key and rely on the client to thread it. The InvokeFunctionTool
approval/local-function half of
|
||
|
|
4b5a8478de |
.NET: Hosting updates to declarative workflows (#5589)
* Make DeclarativeWorkflowExecutor ChatProtocol-compatible for AsAIAgent hosting Extends the existing DeclarativeWorkflowExecutor<TInput> root executor with additional ChatProtocol-compatible input routes (string, ChatMessage, IEnumerable<ChatMessage>, ChatMessage[], TurnToken) so that workflows built via DeclarativeWorkflowBuilder.Build<TInput>(...) work both for direct invocation and when hosted via Workflow.AsAIAgent(...). - Each input message advances the declarative graph immediately; the TurnToken that the host sends after the message batch is treated as a no-op since the message has already been processed. - Conversation id resolution now prefers persisted workflow system state, then DeclarativeWorkflowOptions.ConversationId, then a newly created conversation. This makes multi-turn invocations reuse the prior conversation rather than creating a fresh one each turn. - The separate DeclarativeChatProtocolStartExecutor and DeclarativeWorkflowBuilder.BuildChatProtocol overloads introduced earlier are removed; callers continue to use Build<TInput>(...). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: use DeclarativeWorkflowContext when reading workflow conversation id GetWorkflowConversation() requires a DeclarativeWorkflowContext (it calls ReadState which dynamic-casts via the DeclarativeContext helper). The chat-protocol auxiliary handlers receive a BoundWorkflowContext, so calling the extension on the raw IWorkflowContext throws `Invalid workflow context: BoundWorkflowContext`. Use the wrapped declarativeContext that we already constructed. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: surface ExecutorFailedEvent as ErrorContent in AsAIAgent response WorkflowSession.InvokeStageAsync only converted WorkflowErrorEvent into an ErrorContent payload. ExecutorFailedEvent fell through to the default branch which emits an empty AgentResponseUpdate carrying the event in RawRepresentation. OutputConverter then mapped that to a workflow_action item with status=failed and dropped the exception entirely, so callers got status=completed and error=null even when an executor threw. - WorkflowSession.cs: add ExecutorFailedEvent case mirroring WorkflowErrorEvent. Honors _includeExceptionDetails. - OutputConverter.cs: when an update carries both a WorkflowEvent in RawRepresentation and non-empty Contents, fall through to content processing so the unwrapped error (or any future content payload from a workflow event) is actually emitted. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * improve: walk inner exceptions when surfacing ExecutorFailedEvent DeclarativeActionExecutor wraps inner exceptions in DeclarativeActionException with a generic `Unhandled workflow failure` message, hiding the real cause. Walk InnerException so the response shows the full chain (e.g. the underlying HTTP 400 / auth error). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Surface declarative SendActivity output as chat content SendActivityExecutor now emits AgentResponseEvent in addition to MessageActivityEvent so chat protocols (e.g. AsAIAgent) receive the formatted activity text. The existing MessageActivityEvent is preserved for DevUI/observability. Also extend WorkflowSession.WorkflowOutputEvent handling to accept AgentResponse payloads, mapping them to their constituent ChatMessages. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Persist hosted-agent sessions to disk; fix System.LastMessageText Adds FileSystemAgentSessionStore that writes the serialized AgentSession JSON (which already embeds the workflow's in-memory checkpoint manager) to a per- conversation file under /.checkpoints when running in a Foundry hosted env or {cwd}/.checkpoints locally. Mirrors the python foundry_hosting._responses FileCheckpointStorage pattern so multi-turn workflow state survives process restarts without requiring callers to wire up storage themselves. AddFoundryResponses now defaults to FileSystemAgentSessionStore.CreateDefault() instead of InMemoryAgentSessionStore; callers can still override via DI. Also fixes {System.LastMessageText} resolving empty: DeclarativeWorkflowExecutor .AdvanceAsync was passing the message rehydrated from CreateMessageAsync to SetLastMessageAsync, but ResponseItem -> ChatMessage round-trip drops the .Text extension content. Use the original input ChatMessage (which still has the user-supplied text) and copy the server-assigned MessageId across when present. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Close multi-modal input parity gaps with python foundry_hosting InputConverter now mirrors the python _responses.py content handling: - ComputerScreenshotContent maps to UriContent/HostedFileContent (was dropped). - Plain TextContent and SummaryTextContent map to MEAI TextContent. - MessageContentReasoningTextContent maps to MEAI TextReasoningContent. - input_file with text/* file_data data URIs is decoded inline into TextContent with a [File: name] prefix, matching python _convert_file_data so {System.LastMessageText} surfaces the file body. Non-text data URIs and hosted/url file references preserve filename as AdditionalProperties. Image/file extraction logic is extracted into shared AppendImageContent and AppendFileContent helpers used by both the fresh-input and history-replay switches. Existing 37 InputConverter tests still pass. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Foundry hosting: round-trip tool-approval (HITL) content as mcp_approval_request/response Closes the gap where Microsoft.Agents.AI.Foundry.Hosting silently dropped MEAI ToolApprovalRequestContent/ToolApprovalResponseContent in both directions. We now serialize them onto the wire as the standard Responses API mcp_approval_request/mcp_approval_response items with server_label='agent_framework', and parse the symmetric inbound shapes back into MEAI content. Wire format: - The Responses API only standardizes mcp_approval_* as the approval primitive. We declare AF as a virtual MCP server via the server_label field, which is honest for AF's server-side tool-call holding pattern. - The SDK enforces a strict {prefix}_{50hex} wire-id format, so we hash the AF RequestId and persist a wireId<->afRequestId mapping in AgentSession.StateBag so a later mcp_approval_response can be matched back to the originating workflow request. Coexists with the existing ConsentAwareMcpClientAIFunction flow (AgentFrameworkResponseHandler.cs) which emits mcp_approval_request from a side-channel, not via OutputConverter's content switch. Known follow-up: python (foundry_hosting/_responses.py) has the same output-side gap (ToolApprovalRequestContent emission). Out of scope here. Tests: +9 unit tests covering both fresh-input and history-replay shapes, StateBag mapping resolution, and the non-FunctionCallContent skip path. Existing 108 converter tests still pass; full suite 370/370. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR review feedback for hosted-declarative-dotnet FileSystemAgentSessionStore reliability/scoping: - Bound Sanitize() stackalloc at 256 chars, fall back to ArrayPool for longer ids so a long conversationId can no longer crash the hosting process with StackOverflowException. - Use a Guid-suffixed temp file (\{path}.{guid}.tmp\) so concurrent SaveSessionAsync calls on the same conversation can no longer race on the same temp file. Best-effort temp cleanup on failure. - Bucket session files by agent.Name when set so two keyed agents that happen to share a conversationId no longer overwrite each other's persisted state. Single-agent / unnamed-agent cases keep the original flat layout (Python parity). DeclarativeWorkflowExecutor chat-protocol routing: - ConfigureChatProtocolRoutes uses IsAssignableFrom rather than exact type equality so a broader TInput (object, base interfaces) does not have its inherited inputTransform shadowed by handlers we register here. - HandleChatMessagesAsync / HandleChatMessageArrayAsync now advance through every message in the batch instead of keeping only the trailing one, so multi-message turns and replayed history are no longer silently truncated. AdvanceAsync gains a finalizeTurn flag so only the last message in the batch sends the result. Tests: - New FileSystemAgentSessionStoreTests covering constructor, fresh-session fallback for missing/empty files, root-directory creation, save/get round-trip, agent-Name scoping isolation, long conversationId, invalid-character sanitization, and concurrent-save behavior. - New InputConverterTests covering AppendFileContent: text/* data URI decode (with and without filename prefix), non-text data URI passthrough, malformed data URI fallback, and filename propagation onto UriContent / HostedFileContent. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add tests for remaining PR review feedback (C2, D1, E1) C2: InputConverter — add 9 tests covering SDK content types that previously had no coverage: - SdkTextContent → TextContent (input + output paths) - SummaryTextContent → TextContent (input + output paths) - MessageContentReasoningTextContent → TextReasoningContent (input + output) - ComputerScreenshotContent (HTTP URL → UriContent, data: URI → DataContent, output path → UriContent) D1: OutputConverter — add 2 tests for the WorkflowEvent + Contents fall-through: - WorkflowEvent in RawRepresentation with text Contents must flow through the content-processing path (text-delta event emitted). - WorkflowEvent + ErrorContent must produce a failed event rather than be swallowed by the workflow branch. E1: SendActivityExecutor — extend CaptureActivityAsync to assert that the executor emits an AgentResponseEvent carrying the activity text with the correct ExecutorId and ChatRole.Assistant role. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Defense-in-depth: neutralize dot-segments in Sanitize and cap TryDecodeTextDataUri input size Addresses claude-opus-4.6 security review on PR #5589: - FileSystemAgentSessionStore.Sanitize now replaces all-dot segments (., .., ...) with underscores so a developer-controlled agent.Name cannot escape the root directory on Linux (where Path.GetInvalidFileNameChars only contains NUL and '/'). - InputConverter.TryDecodeTextDataUri rejects encoded payloads larger than 16 MiB before calling Convert.FromBase64String, preventing a single oversized data URI from triggering a multi-megabyte allocation. - Adds unit tests covering both fixes. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix Linux-only failure in SaveSessionAsync_SanitizesInvalidPathCharactersAsync '?' is in Path.GetInvalidFileNameChars only on Windows, not on Linux/macOS, so the test failed on Ubuntu in CI. Use Path.GetInvalidFileNameChars()[0] (skipping NUL) to pick a guaranteed-invalid character for the running OS, and assert the result no longer contains it. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address claude-opus-4.6 security/reliability review feedback WorkflowSession.cs: - ExecutorFailedEvent handler no longer leaks the internal executor ID in error messages. Mirror the WorkflowErrorEvent pattern: surface the exception's Message when _includeExceptionDetails is true, fall back to the generic 'An error occurred while executing the workflow.' otherwise. This also resolves the failing WorkflowHostSmokeTests assertions. FileSystemAgentSessionStore.cs: - GetSessionPath no longer has a write side effect. Directory.CreateDirectory for the per-agent bucket is now performed only on the SaveSessionAsync path, so a read miss on GetSessionAsync no longer leaves an empty directory on disk. - Adds GetSessionAsync_NoExistingFile_DoesNotCreateAgentDirectoryAsync to lock in the no-side-effect-on-read contract. OutputConverterTests.cs: - Strengthen ConvertUpdatesToEventsAsync_ToolApprovalRequest_NonFunctionToolCall_SkippedAsync to assert exactly one event (the terminal ResponseCompletedEvent) so a spurious output-item-added/-done leak would now fail the test. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR review: clean up comments and rename TryParseArguments - Remove Python-codebase references from C# XML docs and inline comments. - Drop fix-history comments referring to previously-resolved issues. - Drop `Defense-in-depth:` prefixes; keep the concrete `what & why`. - Drop `previously we kept only the trailing message` comment in DeclarativeWorkflowExecutor; just describe current loop behavior. - Rename InputConverter.TryParseArguments to ParseFunctionArgumentsObject to make the intent obvious at the call site. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR review: collision-free Sanitize, MAF-style refactors - FileSystemAgentSessionStore.Sanitize now percent-encodes invalid chars (and `%` itself) instead of replacing them with `_`, eliminating collisions like `foo/bar` vs `foo_bar` mapping to the same bucket. All-dot segments encode every dot so Windows trailing-dot trimming cannot reintroduce a navigable name. - AddFoundryResponses XML doc updated to accurately describe the default store root (/.checkpoints when hosted, {cwd}/.checkpoints locally). - DeclarativeWorkflowExecutor.ConfigureChatProtocolRoutes now uses exact type equality instead of IsAssignableFrom so a broad TInput (e.g. object) does not skip registering IEnumerable<ChatMessage>, which ChatProtocolExtensions.IsChatProtocol requires verbatim. - SendActivityExecutor uses context.YieldOutputAsync(response) instead of manually constructing AgentResponseEvent, so the activity will participate in any future OutputFilter coverage. - WorkflowSession handles AgentResponseEvent in its own switch case, avoiding the second typecheck against output.Data. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(workflows): bridge declarative HITL through Foundry hosting via IExternalRequestEnvelope Introduce a new public interface IExternalRequestEnvelope in Microsoft.Agents.AI.Workflows that lets the runtime peek through a declarative-layer envelope without taking a circular reference back into the declarative package. ExternalInputRequest (declarative) implements it; ExternalInputResponse is constructed via the request's CreateResponse factory. WorkflowSession unwraps inner AIContent on the request side and rewraps the client's ChatMessage reply into an ExternalInputResponse on the response side. PortableValue cannot deserialize directly into an interface, so TryGetRequestEnvelope resolves the concrete type via RequestPortInfo.RequestType (TypeId -> Type.GetType) before casting. Public WorkflowHarness contract preserved: InvokeFunctionToolExecutor and WorkflowActionVisitor are unchanged from upstream, so public InvokeToolWorkflowTest scenarios continue to drive ExternalInputRequest / ExternalInputResponse directly through the harness. AgentFrameworkResponseHandler: skip prior conversation history replay when an existing session is being resumed (workflow checkpoint already holds the prior messages). WorkflowSession: when includeExceptionDetails is opted in, also unwrap DeclarativeActionException so HITL failures are debuggable. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
|
75a8335af5 |
.NET - [Breaking]: Update Declarative Object Model + Dependencies (#3017)
* Builds locally and tests pass * Fix typo * Reverted nuget config change to remove internal feed and map to new public object model package with renames. * Renaming Bot object model in additional sample. --------- Co-authored-by: Peter Ibekwe <peibekwe@microsoft.com> |
||
|
|
5902bcb10a |
.NET: [BREAKING] Propagate CancellationToken into Workflow Executors and message handlers (#1280)
* feat: Propagate CancellationToken to Executors * Also adds cancellation propagation to `Executor`-accessible APIs * Adds registrators for cancellable handlers to `RouteBuilder` * [BREAKING]: Adds `CancellationToken` to `IMessageHandler.HandleAsync` * test: Re-enable Concurrent Orchestration test * refactor: Delete unused IInputCoordinator * refactor: Remove superfluous argument qualifications |
||
|
|
2539282d30 |
.NET: Fix some more static analysis diagnostics (#1025)
* S1006 * S2219 * S3236 * S3260 * S1125 * IDE0063 * IDE0062 * IDE0028 |
||
|
|
647db9635a |
.NET: Rename workflows projects (#975)
* Renaming Microsoft.Agent.Workflows to Microsoft.Agents.AI.Workflows * Removing local settings. * Removing remining old files from merge. |