8 Commits

• Fix PR comments
  Peter Ibekwe · 2026-06-15 17:42:12 -07:00
  2c6c17054e
• Declarative workflow bugfix
  Peter Ibekwe · 2026-06-15 16:43:10 -07:00
  61378eee01
• .NET: Bug fixes for declarative workflows (#6427)

  * declarative workflow approval flow fix
  
  * Update mcp handler cache construction
  
  * fix method argument.
  
  * Update dotnet/src/Microsoft.Agents.AI.Workflows.Declarative/ObjectModel/InvokeFunctionToolExecutor.cs
  
  Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
  
  * Fix identation
  
  ---------
  
  Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

  Peter Ibekwe · 2026-06-10 18:08:32 +00:00
  3753d938f5
• .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 1baf4af4d remains.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Set Foundry ProductContext per-executor instead of via PropertyPath workaround
  
  ObjectModel 2026.2.4.1 resolves PropertyPath.VariableName / NamespaceAlias and VariableScopeNames.IsValidName against AsyncLocal<ProductContext> at access time. In hosted-agent scenarios each HTTP request runs on a fresh async context where that AsyncLocal is default, so dotted refs like Local.Triage returned null and the Local scope alias was rejected.
  
  Replace the PropertyPathExtensions helper (which papered over both symptoms) with a single WorkflowDiagnostics.SetFoundryProduct() call at the entry of DeclarativeActionExecutor.HandleAsync. The set writes to the request's logical async context before any code reads PropertyPath, letting the existing parser and scope resolver work as designed.
  
  Validated: 824/824 declarative unit tests pass; technical/billing/general routes all dispatch correctly against a deployed Foundry hosted agent.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Address review feedback on InvokeFunctionToolExecutor
  
  - Surface registered-function lookup failures and invocation exceptions via FunctionResultContent.Exception instead of returning the error text as a successful Result, so downstream {Local.X} assignments can distinguish failures from successes.
  
  - Use AIJsonUtilities.DefaultOptions to JSON-serialize non-string function results (matching FunctionInvokingChatClient / ToolBridge), so complex types stay consumable by PropertyPath consumers instead of degrading to Object.ToString().
  
  - Drop the explicit System. prefix on StringComparison / Exception now that the file imports System.
  
  - Add AutoSendTrueOnExternalConversationEmitsResponseEventsAndCopiesMessagesAsync to cover the (autoSend: true, external conversation) quadrant, asserting that response events are emitted and that messages are mirrored to the workflow conversation.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Honor AutoSendIsDefaultValue when computing autoSend
  
  AzureAgentOutput.AutoSend and InvokeToolOutput.AutoSend in
  Microsoft.Agents.ObjectModel 2026.2.4.1 are never null — they
  return a literal-false default when the YAML omits the field.
  The previous null check in Get/AutoSendValue therefore always
  fell through to evaluating the literal false, so every action
  whose YAML had any output block but no explicit autoSend was
  treated as autoSend = false. This was previously masked by
  `autoSend |= isWorkflowConversation` in AgentProviderExtensions
  (removed earlier in this PR to honor explicit autoSend: false),
  which silently re-enabled autoSend on the workflow conversation.
  
  Use AutoSendIsDefaultValue to distinguish an explicit autoSend
  value from the implicit default and treat the implicit default
  as true, restoring the historical behavior for ValidateCaseAsync
  InvokeAgent.yaml (3 InvokeAzureAgent actions, last one captures
  to Local.RatingResponse via output.messages with no autoSend
  specified) while keeping the hosted-agent fix that honors an
  explicit autoSend: false.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  ---------
  
  Co-authored-by: Ben Thomas <25218250+alliscode@users.noreply.github.com>
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

  Ben Thomas · 2026-05-22 01:06:38 +00:00
  b559545fa4
• .NET: Update to OpenAI 2.9.1, Azure.AI.OpenAI 2.9.0-beta.1, Microsoft.Extensions.AI 10.4.0, and Azure.AI.Projects 2.0.0-beta.2 (#4613)

  * Initial plan
  
  * Update code for Microsoft.Extensions.AI.Abstractions 10.4.0 breaking changes
  
  - Rename FunctionApprovalRequestContent → ToolApprovalRequestContent
  - Rename FunctionApprovalResponseContent → ToolApprovalResponseContent
  - Rename UserInputRequestContent → ToolApprovalRequestContent
  - Rename UserInputResponseContent → ToolApprovalResponseContent
  - Update .FunctionCall property → .ToolCall with FunctionCallContent casts where needed
  - Update .Id property → .RequestId on the renamed types
  - Rename FunctionApprovalRequestEventGenerator → ToolApprovalRequestEventGenerator
  - Rename FunctionApprovalResponseEventGenerator → ToolApprovalResponseEventGenerator
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Update OpenAI 2.9.1, ME.AI 10.4.0, fix breaking API changes
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Fix remaining ME.AI 10.4.0 breaking changes: MCP approval types, .Output→.Outputs
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Use pattern matching with `when` for ToolApprovalRequestContent/FunctionCallContent
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Update Azure.AI.OpenAI to 2.9.0-beta.1
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Fix remaining GetResponsesClient(model) build failures for Azure.AI.OpenAI 2.9.0-beta.1
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Address review feedback: remove redundant type checks in TestRequestAgent.cs and fix error message in AIAgentHostExecutor.cs
  
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  
  * Update Azure.AI.Projects to 2.0.0-beta.2 with namespace migration
  
  - Azure.AI.Projects 2.0.0-beta.1 → 2.0.0-beta.2
  - Azure.AI.Projects.OpenAI → Azure.AI.Extensions.OpenAI (transitive)
  - Agent types moved to Azure.AI.Projects.Agents namespace
  - AgentRecord.Versions.Latest → AgentRecord.GetLatestVersion()
  - OpenAPIFunctionDefinition → OpenApiFunctionDefinition
  - BingCustomSearchToolParameters → BingCustomSearchToolOptions
  - MemorySearchPreviewTool.UpdateDelay → UpdateDelayInSecs
  - Azure.Identity 1.17.1 → 1.19.0
  - Microsoft.Identity.Client.Extensions.Msal 4.78.0 → 4.83.1
  
  Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
  
  * Fix remaining type renames for Azure.AI.Projects 2.0.0-beta.2
  
  - BrowserAutomationToolParameters → BrowserAutomationToolOptions
  - MemoryUpdateOptions.UpdateDelay stays as UpdateDelay (not renamed)
  - WaitForMemoriesUpdateAsync parameter order: pollingInterval before options
  - AIProjectAgentsOperations → AgentsClient
  
  Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
  
  * Fix format errors and OpenTelemetry test for ME.AI 10.4.0
  
  - Remove unused 'using Azure.AI.Extensions.OpenAI' and fix import ordering
    in Agent_With_AzureAIProject/Program.cs
  - Update OpenTelemetryAgentTests: gen_ai.tool.definitions is now always
    emitted regardless of EnableSensitiveData per ME.AI 10.4.0 change
    (dotnet/extensions#7346). Tool definitions are not considered sensitive.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Fix GetRepoFolder() to work in git worktrees
  
  Use 'workflow-samples' directory as repo root marker instead of '.git',
  which fails in worktrees (.git is a file) and also matches too early
  when a '.github' folder exists in subdirectories.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Fix formatting: remove unused usings and fix import ordering
  
  dotnet format applied across 59 impacted projects. Primarily removes
  unnecessary 'using Azure.AI.Projects' where Azure.AI.Projects.Agents
  provides all needed types, and fixes import ordering per editorconfig.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Disable AzureAIAgentsPersistent integration tests (#4769)
  
  Azure.AI.Agents.Persistent 1.2.0-beta.9 references McpServerToolApprovalResponseContent
  which was removed in ME.AI 10.4.0 (renamed to ToolApprovalResponseContent), causing
  TypeLoadException at runtime. Mark all 6 test classes with IntegrationDisabled trait
  until Persistent ships a version targeting ME.AI 10.4.0+.
  
  Upstream fix: https://github.com/Azure/azure-sdk-for-net/pull/56929
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Add README with compatibility note for AzureAI.Persistent (#4769)
  
  Documents that Azure.AI.Agents.Persistent 1.2.0-beta.9 is only compatible
  with ME.AI ≤10.3.0 and OpenAI ≤2.8.0 due to type renames in ME.AI 10.4.0.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Fix file encoding: restore UTF-8 BOM on Persistent test files
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Mark AzureAI.Persistent as IsPackable=false (#4769)
  
  Prevent shipping until Azure.AI.Agents.Persistent targets ME.AI 10.4.0+.
  
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  
  * Moving IsPackable after import
  
  ---------
  
  Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
  Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
  Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>
  Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

  Copilot · 2026-03-20 14:29:29 +00:00
  88ea9d08c7
• .NET: Support InvokeMcpTool for declarative workflows (#4204)

  * Initial implementation of InvokeMcpTool in declarative workflow
  
  * Cleaned up sample implementation
  
  * Updated sample comments.
  
  * Added missing executor routing attribute
  
  * Fix PR comments.
  
  * Updated based on PR comments.
  
  * Updated based on PR comments.
  
  * Removed unnecessary using statement.

  Peter Ibekwe · 2026-02-25 19:21:36 +00:00
  de9d886aba
• .NET: [BREAKING] Implement Polymorphic Routing (#3792)

  * feat: Implement Polymorphic Routing
  
  * feat: Add support for Send/Yield annotations with basic Executor
  
  * Adds annotations to Declarative workflow executors
  
  * fix: Address PR Comments
  
  * Implicit filter in collection loops
  * Remove debug / usused / superfluous code
  * Fix ProtocolBuilder implicit output registrations
  * Fix logic error in ExecuteRouteGeneratorTests.ClassWithManualConfigureProtocol_DoesNotGenerate
  
  * fix: Solidify type checks and send/yield type registrations
  
  * fix: Suppress generation of TurnTokens out of AggregateTurnMessagesExecutor
  
  * Fixes an issue where ConcurrentEndExecutor is not expecting TurnTokens.
  
  * fix: Add ProtocolBuilder support for chained-delegation
  
  * Updates Declarative pacakge to rely on chained-delegation Send/Yield registration
  * Renames DeclarativeActionExectuor's new ExecuteAsync to ExecuteActionAsync to avoid colliding with Executor.ExecutoeAsync
  
  * fix: Address PR Comments
  
  * Fixes type mapping in FanInEdgeRunner
  * Fixes and expalins send/yield type registration in FunctionExecutor
  
  * fixup: build-break
  
  * fix: Add missing SendsMesage declaration to InvokeAzureAgentExecutor

  Jacob Alber · 2026-02-19 14:09:03 +00:00
  6a3d22598f
• .NET: Support InvokeFunctionTool for declarative workflows (#4014)

  * Initial Implementation of InvokeFunctionTool
  
  * Added unit test for InvokeFunctionTool executor.
  
  * Implemented unit and integration tests for InvokeFunctionTool.
  
  * Add sample for InvokeFunctionTool in declarative workflows.
  
  * Remove unused sample and updated comments.
  
  * Updating to official OM release with InvokeFunctionTool
  
  * Fix formatting issues.
  
  * Updated PowerFx version
  
  * Update test fixture
  
  * Cleanup - Removed unused method in InvokeFunctionToolExecutor
  
  * Update test based on PR feedback.
  
  * Update based on PR comments

  Peter Ibekwe · 2026-02-18 23:15:36 +00:00
  988ef6a50e