agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

.NET Workflows - WIP Declarative action update (#1761)

Browse Source 
* WIP

* Fixed build errors (#1638)

Comment and nullable type alignment

* Sync to SDK update

* Checkpoint

* Checkpoint: Tests passing

* Checkpoint: EndWorkflow

* Add trace

* .NET: Azure.AI.Agents Package Split + Initial Extensions (#1657)

* Move packages

* Update nuget.config

* Address Xmldoc

* Remove format from branches checks

* Address Xmldocs

* Add more details to the implementation

* Moving Agent logic to ChatClient

* Adding Name and Id overrides to AzureAIAgent

* Updating extensions

* Add GetAiAgent extensions

* Adding support for version as name can conflict 409 using the Agents API with same name

* Addressing more updates to the extensions

* More improvements

* Remove debugging code from sample

* Address copilot feedback

* Apply suggestions from co-pilot code review

* Checkpoint

* Update Directory.Packages.props

Fix package version rollback:

Azure.AI.Agents.Persistent (beta-6 => beta-7)

* Add project reference

* .NET: Add comprehensive unit tests for Microsoft.Agents.AI.AzureAIAgents extension methods (#1786)

* Initial plan

* Add comprehensive unit test project for Microsoft.Agents.AI.AzureAIAgents

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Add README documenting test project and package dependency requirements

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Fix documentation URL to use learn.microsoft.com

Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>

* Bump back AAAP 1.2.0-beta.7

* Address AI generated UT's

* Remove UT Readme

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* .NET: Change model to be required just for prompt agent definition specific extensions (#1812)

* Remove unneeded model from extensions

* Add noop justification

* Update Package Nameing: V1 -> AzureAI.Persistent / V2 -> AzureAI (#1829)

* Checkpoint for merge

* No build errors

* .NET: Update Extensions for Strict Agent Definitions + Improvements (#1892)

* Update Package Nameing: V1 -> AzureAI.Persistent / V2 -> AzureAI

* Update agents and extensions to comply with strict agent definitions

* More static updates

* Address UT, and ResponseTool support

* Improving reusability extensions

* Addressing ResponseTools Unit Tests and extension setup

* Adapted workaround on breaking AAA with OpenAI 2.6.0

* Small updates

* Remove strictness when retrieving agents, improved XmlDocs

* Improve sample comments

* Update dotnet/tests/Microsoft.Agents.AI.AzureAI.UnitTests/AgentsClientExtensionsTests.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Address PR comments

* Address UT failing

* Address Copilot feedback

* Address Copilot feedback

* Address comment typo

* Address PR feedback

* Address typo

* Add missing Extensions with ChatClientAgentOptions

* Address comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Updated package version (#1897)

* Version update (#1901)

* Checkpoint

* Updated package version (#1906)

* Checkpoint

* Checkpoint

* Checkpoint

* Align with azure ai agent

* Update dotnet/samples/GettingStarted/Workflows/Declarative/StudentTeacher/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/MCPToolApproval/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/DeepResearch/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Refactored external input

* Update dotnet/samples/GettingStarted/Workflows/Declarative/MCPToolApproval/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Agent tools patch

* Demos validated

* Checkpoint

* Hygiene

* Checkpoint - Samples

* Update dotnet/samples/GettingStarted/Workflows/Declarative/StudentTeacher/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/StudentTeacher/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Checkpoint

* Checkpoint - Deep Research

* Update baseline

* Update

* Typo

* Checkpoint

* Typos

* Sample cleanup

* Update dotnet/src/Microsoft.Agents.AI.Workflows.Declarative/AzureAgentProvider.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/src/Microsoft.Agents.AI.AzureAI/AgentsClientExtensions.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/FunctionTools/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/StudentTeacher/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/ToolApproval/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update dotnet/samples/GettingStarted/Workflows/Declarative/DeepResearch/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Typo

* Typo

* Fix input loop

* Sample - Function Calling / External Input

* Typo

* Finessed

* Checkpoint

* Fix feed

* Checkpoint - so close

* Ding dong!

* "there" ***

* Fixup comments

* Fix sample

* Code analysis

* Header

* Typo (variableName)

* Remove dead code

* Skip test (agent api ratchet)

* Comment

* Update dotnet/samples/GettingStarted/Workflows/Declarative/StudentTeacher/Program.cs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Typo

---------

Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
This commit is contained in:
Chris
2025-11-07 11:37:21 -08:00
committed by GitHub
Unverified
parent 7c3d4fcf30
commit 2b869c2396
125 changed files with 3192 additions and 3712 deletions
Download Patch File Download Diff File Expand all files Collapse all files
workflow-samples/DeepResearch.yaml
+83 -224
View File
@@ -2,33 +2,18 @@
# This workflow coordinates multiple agents in order to address complex user requests
# according to the "Magentic" orchestration pattern introduced by AutoGen.
#
# For this workflow, several agents used, each with a prompt specific to their role:
# For this workflow, several agents used, each with specific roles.
#
# 1. Analyst Agent: Able to analyze the current task.
# Enable "Bing Grounding Tool" in the agent settings.
# See: ./setup/AnalystAgent.yaml
#
# 2. Manager Agent: Able to create plans and delegate tasks to other agents.
# See: ./setup/ManagerAgent.yaml
#
# 3. Research Agent:
# Enable "Bing Grounding" in the agent settings.
# See: ./setup/WebAgent.yaml
# The following agents are responsible for overseeing and coordinating the workflow:
# - Research Agent: Analyze the current task and correlate relevant facts.
# - Planner Agent: Analyze the current task and devise an overall plan.
# - Manager Agent: Evaluates status and delegate tasks to other agents.
# - Summary Agent: Evaluates status and delegate tasks to other agents.
#
# With instructions:
#
# Only provide requested information in a way that is throughfully organized and formatted.
# Never include any analysis or code.
# Never generate a file.
# Avoid repeating yourself.
#
# 4. Coder Agent:
# Enable "Code Interpreter" in the agent settings.
# See: ./setup/CoderAgent.yaml
#
# 5. Weather Agent: Able to retrieve factual information from the web.
# Enable "Open API" in the agent settings using the wttr.json schema.
# See: ./setup/WeatherAgent.yaml
# The following agents have capabilities that are utilized to address the input task:
# - Knowledge Agent: Performs generic web searches.
# - Coder Agent: Able to write and execute code.
# - Weather Agent: Provides weather information.
#
kind: Workflow
trigger:
@@ -45,18 +30,15 @@ trigger:
=[
{
name: "WeatherAgent",
description: "Able to retrieve weather information",
agentid: Env.FOUNDRY_AGENT_RESEARCHWEATHER
description: "Able to retrieve weather information"
},
{
name: "CoderAgent",
description: "Able to write and execute Python code",
agentid: Env.FOUNDRY_AGENT_RESEARCHCODER
description: "Able to write and execute Python code"
},
{
name: "WebAgent",
description: "Able to perform generic websearches",
agentid: Env.FOUNDRY_AGENT_RESEARCHWEB
name: "KnowledgeAgent",
description: "Able to perform generic websearches"
}
]
@@ -84,38 +66,22 @@ trigger:
- kind: CreateConversation
id: conversation_1a2b3c
conversationId: Local.InternalConversationId
conversationId: Local.StatusConversationId
- kind: CreateConversation
id: conversation_1x2y3z
conversationId: Local.TaskConversationId
- kind: InvokeAzureAgent
id: question_UDoMUw
displayName: Get Facts
conversationId: =Local.InternalConversationId
conversationId: =Local.StatusConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHANALYST
name: ResearchAgent
output:
autoSend: false
messages: Local.TaskFacts
input:
messages: =UserMessage(Local.InputTask)
additionalInstructions: |-
In order to help begin addressing the user request, please answer the following pre-survey to the best of your ability.
Keep in mind that you are Ken Jennings-level with trivia, and Mensa-level with puzzles, so there should be a deep well to draw from.
Here is the pre-survey:
1. Please list any specific facts or figures that are GIVEN in the request itself. It is possible that there are none.
2. Please list any facts that may need to be looked up, and WHERE SPECIFICALLY they might be found. In some cases, authoritative sources are mentioned in the request itself.
3. Please list any facts that may need to be derived (e.g., via logical deduction, simulation, or computation)
4. Please list any facts that are recalled from memory, hunches, well-reasoned guesses, etc.
When answering this survey, keep in mind that 'facts' will typically be specific names, dates, statistics, etc. Your answer must only use the headings:
1. GIVEN OR VERIFIED FACTS
2. FACTS TO LOOK UP
3. FACTS TO DERIVE
4. EDUCATED GUESSES
DO NOT include any other headings or sections in your response. DO NOT list next steps or plans until asked to do so.
- kind: SendActivity
id: sendActivity_yFsbRz
@@ -124,52 +90,42 @@ trigger:
- kind: InvokeAzureAgent
id: question_DsBaJU
displayName: Create a Plan
conversationId: =Local.InternalConversationId
conversationId: =Local.StatusConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
name: PlannerAgent
inputs:
arguments:
team: =Local.TeamDescription
output:
autoSend: false
messages: Local.Plan
input:
messages: =UserMessage(Local.InputTask)
additionalInstructions: |-
Your only job is to devise an efficient plan that identifies (by name) how a team member may contribute to addressing the user request.
Only select the following team which is listed as "- [Name]: [Description]"
{Local.TeamDescription}
The plan must be a bullet point list must be in the form "- [AgentName]: [Specific action or task for that agent to perform]"
Remember, there is no requirement to involve the entire team -- only select team member's whose particular expertise is required for this task.
- kind: SetVariable
- kind: SetTextVariable
id: setVariable_Kk2LDL
displayName: Define instructions
variable: Local.TaskInstructions
value: |-
="# TASK
# TASK
Address the following user request:
" & Local.InputTask & "
{Local.InputTask}
# TEAM
Use the following team to answer this request:
" & Local.TeamDescription & "
{Local.TeamDescription}
# FACTS
Consider this initial fact sheet:
" & Trim(Last(Local.TaskFacts).Text) & "
{Trim(Last(Local.TaskFacts).Text)}
# PLAN
Here is the plan to follow as best as possible:
" & Last(Local.Plan).Text
{Last(Local.Plan).Text}
- kind: SendActivity
id: sendActivity_bwNZiM
@@ -178,131 +134,41 @@ trigger:
- kind: InvokeAzureAgent
id: question_o3BQkf
displayName: Progress Ledger Prompt
conversationId: =Local.InternalConversationId
conversationId: =Local.StatusConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
output:
autoSend: false
messages: Local.ProgressLedgerUpdate
name: ManagerAgent
input:
messages: =UserMessage(Local.AgentResponseText)
additionalInstructions: |-
Recall we are working on the following request:
{Local.InputTask}
And we have assembled the following team:
{Local.TeamDescription}
To make progress on the request, please answer the following questions, including necessary reasoning:
- Is the request fully satisfied? (True if complete, or False if the original request has yet to be SUCCESSFULLY and FULLY addressed)
- Are we in a loop where we are repeating the same requests and / or getting the same responses from an agent multiple times? Loops can span multiple turns, and can include repeated actions like scrolling up or down more than a handful of times.
- Are we making forward progress? (True if just starting, or recent messages are adding value. False if recent messages show evidence of being stuck in a loop or if there is evidence of significant barriers to success such as the inability to read from a required file)
- Who should speak next? (select from: {Concat(Local.AvailableAgents, name, ",")})
- What instruction or question would you give this team member? (Phrase as if speaking directly to them, and include any specific information they may need)
Please output an answer in pure JSON format according to the following schema. The JSON object must be parsable as-is. DO NOT OUTPUT ANYTHING OTHER THAN JSON, AND DO NOT DEVIATE FROM THIS SCHEMA:
{{
"is_request_satisfied": {{
"reason": string,
"answer": boolean
}},
"is_in_loop": {{
"reason": string,
"answer": boolean
}},
"is_progress_being_made": {{
"reason": string,
"answer": boolean
}},
"next_speaker": {{
"reason": string,
"answer": string (select from: {Concat(Local.AvailableAgents, name, ",")})
}},
"instruction_or_question": {{
"reason": string,
"answer": string
}}
}}
- kind: ParseValue
id: parse_rNZtlV
displayName: Parse ledger response
variable: Local.TypedProgressLedger
value: =Last(Local.ProgressLedgerUpdate).Text
valueType:
kind: Record
properties:
instruction_or_question:
type:
kind: Record
properties:
answer: String
reason: String
is_in_loop:
type:
kind: Record
properties:
answer: Boolean
reason: String
is_progress_being_made:
type:
kind: Record
properties:
answer: Boolean
reason: String
is_request_satisfied:
type:
kind: Record
properties:
answer: Boolean
reason: String
next_speaker:
type:
kind: Record
properties:
answer: String
reason: String
output:
responseObject: Local.ProgressLedger
- kind: ConditionGroup
id: conditionGroup_mVIecC
conditions:
- id: conditionItem_fj432c
condition: =Local.TypedProgressLedger.is_request_satisfied.answer
condition: =Local.ProgressLedger.is_request_satisfied.answer
displayName: If Done
actions:
- kind: SendActivity
id: sendActivity_kdl3mC
activity: Completed! {Local.TypedProgressLedger.is_request_satisfied.reason}
activity: Completed! {Local.ProgressLedger.is_request_satisfied.reason}
- kind: InvokeAzureAgent
id: question_Ke3l1d
displayName: Generate Response
conversationId: =System.ConversationId
conversationId: =Local.TaskConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
name: SummaryAgent
output:
autoSend: true
messages: Local.FinalResponse
input:
messages: =Local.SeedTask
additionalInstructions: |-
We have completed the task.
Based only on the conversation and without adding any new information, synthesize the result of the conversation as a complete response to the user task.
The user will only every see this last response and not the entire conversation, so please ensure it is complete and self-contained.
- kind: EndConversation
id: end_SVoNSV
- id: conditionItem_yiqund
condition: =Local.TypedProgressLedger.is_in_loop.answer || Not(Local.TypedProgressLedger.is_progress_being_made.answer)
condition: =Local.ProgressLedger.is_in_loop.answer || Not(Local.ProgressLedger.is_progress_being_made.answer)
displayName: If Stalling
actions:
@@ -312,26 +178,25 @@ trigger:
variable: Local.StallCount
value: =Local.StallCount + 1
- kind: ConditionGroup
id: conditionGroup_vBTQd3
conditions:
- id: conditionItem_fpaNL9
condition: =Local.TypedProgressLedger.is_in_loop.answer
condition: =Local.ProgressLedger.is_in_loop.answer
displayName: Is Loop
actions:
- kind: SendActivity
id: sendActivity_fpaNL9
activity: {Local.TypedProgressLedger.is_in_loop.reason}
activity: {Local.ProgressLedger.is_in_loop.reason}
- id: conditionItem_NnqvXh
condition: =Not(Local.TypedProgressLedger.is_progress_being_made.answer)
condition: =Not(Local.ProgressLedger.is_progress_being_made.answer)
displayName: Is No Progress
actions:
- kind: SendActivity
id: sendActivity_NnqvXh
activity: {Local.TypedProgressLedger.is_progress_being_made.reason}
activity: {Local.ProgressLedger.is_progress_being_made.reason}
- kind: ConditionGroup
@@ -366,28 +231,23 @@ trigger:
- kind: InvokeAzureAgent
id: question_wFJ123
displayName: Get New Facts Prompt
conversationId: =Local.InternalConversationId
conversationId: =Local.StatusConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHANALYST
name: ResearchAgent
output:
autoSend: false
messages: Local.TaskFacts
input:
messages: |-
=UserMessage(
"As a reminder, we are working to solve the following task:
"It's clear we aren't making as much progress as we would like, but we may have learned something new.
Please rewrite the following fact sheet, updating it to include anything new we have learned that may be helpful.
Example edits can include (but are not limited to) adding new guesses, moving educated guesses to verified facts if appropriate, etc.
Updates may be made to any section of the fact sheet, and more than one section of the fact sheet can be edited.
This is an especially good time to update educated guesses, so please at least add or update one educated guess or hunch, and explain your reasoning.
" & Local.InputTask)
additionalInstructions: |-
It's clear we aren't making as much progress as we would like, but we may have learned something new.
Please rewrite the following fact sheet, updating it to include anything new we have learned that may be helpful.
Example edits can include (but are not limited to) adding new guesses, moving educated guesses to verified facts if appropriate, etc.
Updates may be made to any section of the fact sheet, and more than one section of the fact sheet can be edited.
This is an especially good time to update educated guesses, so please at least add or update one educated guess or hunch, and explain your reasoning.
Here is the old fact sheet:
Here is the old fact sheet:
{Local.TaskFacts}
{Local.TaskFacts}"
- kind: SendActivity
id: sendActivity_dsBaJU
@@ -396,48 +256,48 @@ trigger:
- kind: InvokeAzureAgent
id: question_uEJ456
displayName: Create new Plan Prompt
conversationId: =Local.InternalConversationId
conversationId: =Local.StatusConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
name: PlannerAgent
output:
autoSend: false
messages: Local.Plan
input:
additionalInstructions: |-
Please briefly explain what went wrong on this last run (the root cause of the failure),
and then come up with a new plan that takes steps and/or includes hints to overcome prior challenges and especially avoids repeating the same mistakes.
As before, the new plan should be concise, be expressed in bullet-point form, and consider the following team composition
(do not involve any other outside people since we cannot contact anyone else):
messages: |-
=UserMessage(
"Please briefly explain what went wrong on this last run (the root cause of the failure),
and then come up with a new plan that takes steps and/or includes hints to overcome prior challenges and especially avoids repeating the same mistakes.
As before, the new plan should be concise, be expressed in bullet-point form, and consider the following team composition
(do not involve any other outside people since we cannot contact anyone else):
{Local.TeamDescription}
{Local.TeamDescription}")
- kind: SetVariable
- kind: SetTextVariable
id: setVariable_jW7tmM
displayName: Set Plan as Context
variable: Local.TaskInstructions
value: |-
="# TASK
# TASK
Address the following user request:
" & Local.InputTask & "
{Local.InputTask}
# TEAM
Use the following team to answer this request:
" & Local.TeamDescription & "
{Local.TeamDescription}
# FACTS
Consider this initial fact sheet:
" & Local.TaskFacts.Text & "
{Local.TaskFacts.Text}
# PLAN
Here is the plan to follow as best as possible:
" & Local.Plan.Text
{Local.Plan.Text}
- kind: SetVariable
id: setVariable_6J2snP
@@ -459,19 +319,14 @@ trigger:
- kind: SendActivity
id: sendActivity_L7ooQO
activity: |-
({Local.TypedProgressLedger.next_speaker.reason})
({Local.ProgressLedger.next_speaker.reason})
{Local.TypedProgressLedger.next_speaker.answer} - {Local.TypedProgressLedger.instruction_or_question.answer}
- kind: SetVariable
id: setVariable_L7ooQO
variable: Local.StallCount
value: 0
{Local.ProgressLedger.next_speaker.answer} - {Local.ProgressLedger.instruction_or_question.answer}
- kind: SetVariable
id: setVariable_nxN1mE
variable: Local.NextSpeaker
value: =Search(Local.AvailableAgents, Local.TypedProgressLedger.next_speaker.answer, name)
value: =Search(Local.AvailableAgents, Local.ProgressLedger.next_speaker.answer, name)
- kind: ConditionGroup
id: conditionGroup_QFPiF5
@@ -480,19 +335,23 @@ trigger:
condition: =CountRows(Local.NextSpeaker) = 1
displayName: If next Agent tool Exists
actions:
- kind: SetVariable
id: setVariable_L7ooQO
variable: Local.StallCount
value: 0
- kind: InvokeAzureAgent
id: question_orsBf06
displayName: Progress Ledger Prompt
conversationId: =System.ConversationId
conversationId: =Local.TaskConversationId
agent:
name: =First(Local.NextSpeaker).agentid
name: =First(Local.NextSpeaker).name
output:
autoSend: true
messages: Local.AgentResponse
input:
messages: =Local.SeedTask
additionalInstructions: |-
{Local.TypedProgressLedger.instruction_or_question.answer}
messages: =UserMessage(Local.ProgressLedger.instruction_or_question.answer)
- kind: SetVariable
id: setVariable_XzNrdM