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 Workflow - Integrated updated CPS Object Model (#681)

Browse Source 
* Checkpoint

* Update workflows/DeepResearch.yaml

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

* Comment

* Fix comment

* Update package version

* Fix nuget haxx

* Checkpoint

* Code complete

* Testing

* Message content workaround

* Add sequential flow

* Checkpoint

* Integration test project

* Checkpoint

* Checkpoint cleanup

* Complete

* Update package

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Chris
2025-09-15 13:41:07 -07:00
committed by GitHub
Unverified
parent db58a10a37
commit 74879489a4
79 changed files with 2830 additions and 685 deletions
Download Patch File Download Diff File Expand all files Collapse all files
workflows/DeepResearch.yaml
+140 -110
View File
@@ -81,54 +81,64 @@ beginDialog:
id: sendActivity_yFsbRy
activity: Analyzing facts...
- kind: AnswerQuestionWithAI
- kind: CreateConversation
id: conversation_1a2b3c
conversationId: Topic.InternalConversationId
- kind: InvokeAzureAgent
id: question_UDoMUw
displayName: Get Facts
autoSend: false
variable: Topic.TaskFacts
userInput: =Topic.InputTask
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHANALYST},
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.
conversationId: =Topic.InternalConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHANALYST
output:
messages: Topic.TaskFacts
input:
messages: =[UserMessage(Topic.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:
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.
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:
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
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.
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
activity: Creating a plan...
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_DsBaJU
displayName: Create a Plan
autoSend: false
variable: Topic.Plan
userInput: =""
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHMANAGER},
Your only job is to devise an efficient plan that identifies (by name) how a team member may contribute to addressing the user request.
conversationId: =Topic.InternalConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
output:
messages: Topic.Plan
input:
messages: =[UserMessage(Topic.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]"
Only select the following team which is listed as "- [Name]: [Description]"
{Topic.TeamDescription}
{Topic.TeamDescription}
The plan must be a bullet point list must be in the form "- [AgentName]: [Specific action or task for that agent to perform]"
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.
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
id: setVariable_Kk2LDL
@@ -162,54 +172,57 @@ beginDialog:
id: sendActivity_bwNZiM
activity: {Topic.TaskInstructions}
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_o3BQkf
displayName: Progress Ledger Prompt
autoSend: false
variable: Topic.ProgressLedgerUpdate
userInput: =Topic.AgentResponseText
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHMANAGER},
Recall we are working on the following request:
conversationId: =Topic.InternalConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
output:
messages: Topic.ProgressLedgerUpdate
input:
messages: =[UserMessage(Topic.AgentResponseText)]
additionalInstructions: |-
Recall we are working on the following request:
{Topic.InputTask}
{Topic.InputTask}
And we have assembled the following team:
And we have assembled the following team:
{Topic.TeamDescription}
{Topic.TeamDescription}
To make progress on the request, please answer the following questions, including necessary reasoning:
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(Topic.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)
- 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(Topic.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:
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(Topic.AvailableAgents, name, ",")})
}},
"instruction_or_question": {{
"reason": string,
"answer": string
}}
}}
{{
"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(Topic.AvailableAgents, name, ",")})
}},
"instruction_or_question": {{
"reason": string,
"answer": string
}}
}}
- kind: ParseValue
id: parse_rNZtlV
@@ -266,16 +279,20 @@ beginDialog:
id: sendActivity_kdl3mC
activity: Completed! {Topic.TypedProgressLedger.is_request_satisfied.reason}
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_Ke3l1d
displayName: Generate Response
variable: Topic.FinalResponse
userInput: =Topic.SeedTask
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHMANAGER},
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.
conversationId: =System.ConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
output:
messages: Topic.FinalResponse
input:
messages: =[UserMessage(Topic.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
@@ -342,45 +359,53 @@ beginDialog:
id: sendActivity_cwNZiM
activity: Re-analyzing facts...
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_wFJ123
displayName: Get New Facts Prompt
autoSend: false
variable: Topic.TaskFacts
userInput: |-
="As a reminder, we are working to solve the following task:
conversationId: =Topic.InternalConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHANALYST
output:
messages: Topic.TaskFacts
input:
messages: |-
=[
UserMessage(
"As a reminder, we are working to solve the following task:
" & Topic.InputTask
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHANALYST},
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.
" & Topic.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:
{Topic.TaskFacts}
{Topic.TaskFacts}
- kind: SendActivity
id: sendActivity_dsBaJU
activity: Re-analyzing plan...
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_uEJ456
displayName: Create new Plan Prompt
autoSend: false
variable: Topic.Plan
userInput: =""
additionalInstructions: |-
{Env.FOUNDRY_AGENT_RESEARCHMANAGER},
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):
conversationId: =Topic.InternalConversationId
agent:
name: =Env.FOUNDRY_AGENT_RESEARCHMANAGER
output:
messages: Topic.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):
{Topic.TeamDescription}
{Topic.TeamDescription}
- kind: SetVariable
id: setVariable_jW7tmM
@@ -452,13 +477,18 @@ beginDialog:
displayName: If next Agent tool Exists
actions:
- kind: AnswerQuestionWithAI
- kind: InvokeAzureAgent
id: question_orsBf06
variable: Topic.AgentResponse
userInput: =Topic.SeedTask
additionalInstructions: |-
{First(Topic.NextSpeaker).agentid},
{Topic.TypedProgressLedger.instruction_or_question.answer}
displayName: Progress Ledger Prompt
conversationId: =System.ConversationId
agent:
name: =First(Topic.NextSpeaker).agentid
output:
messages: Topic.AgentResponse
input:
messages: =[UserMessage(Topic.SeedTask)]
additionalInstructions: |-
{Topic.TypedProgressLedger.instruction_or_question.answer}
- kind: SetVariable
id: setVariable_XzNrdM