Upgrade agent-framework to 1.3.0 and azure-ai-projects to 2.1.0

- Update agent-framework from 1.0.0b260107 to 1.3.0 in pyproject.toml
- Update azure-ai-projects from 1.0.0b12 to 2.1.0 in requirements.txt
- Migrate ChatAgent to Agent (client=, default_options=ChatOptions)
- Migrate agent_framework.azure to agent_framework.openai module paths
- Migrate ChatMessage to Message with Content.from_text()
- Migrate Role enum to string literals
- Migrate AgentRunContext to AgentContext
- Migrate WorkflowBuilder to new API (start_executor=, add_chain)
- Migrate event handling from isinstance checks to WorkflowEvent.type
- Migrate GroupChatBuilder to agent_framework.orchestrations module
- Migrate ContextProvider to before_run/after_run interface
- Remove ToolProtocol (use Any), AgentProtocol (use SupportsAgentRun)
- Define ManagerSelectionResponse locally (removed from framework)
- Update MCP tool files for Agent import
- Update all unit tests for new APIs (812 tests passing)
- Update docs/ProcessFrameworkGuide.md with new WorkflowBuilder example
- Update docs/LocalDevelopmentSetup.md prerelease note
- Regenerate uv.lock

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: Prachig-Microsoft

docs/LocalDevelopmentSetup.md

@@ -337,7 +337,7 @@ py -3.12 -m uv venv .venv
 py -3.12 -m uv sync --prerelease=allow
 ```
 
-> **⚠️ Important**: This repo currently depends on a prerelease/dev version of Microsoft Agent Framework. Always run `uv sync --prerelease=allow` (or `py -3.12 -m uv sync --prerelease=allow` on Windows) after creating the virtual environment to install all required dependencies. Missing dependencies will cause runtime errors like `ModuleNotFoundError: No module named 'pydantic'` or DNS resolution failures.
+> **⚠️ Important**: Always run `uv sync --prerelease=allow` (or `py -3.12 -m uv sync --prerelease=allow` on Windows) after creating the virtual environment to install all required dependencies. The `--prerelease=allow` flag is needed because some transitive dependencies may still use pre-release versions. Missing dependencies will cause runtime errors like `ModuleNotFoundError: No module named 'pydantic'` or DNS resolution failures.
 
 ### 5.4. Run the Processor
 

docs/ProcessFrameworkGuide.md

@@ -118,23 +118,21 @@ Inside each step, the orchestrator can use multi-agent patterns (maker-checker l
 
 - Implementation: [src/processor/src/steps/migration_processor.py](../src/processor/src/steps/migration_processor.py)
 - The processor creates a workflow with `WorkflowBuilder`.
-- It registers four executors, sets the start executor, and defines edges.
+- It instantiates four executors, passes the start executor to `WorkflowBuilder`, and chains them with `add_chain`.
 
 Example from the repo (simplified):
 
 ```python
 from agent_framework import WorkflowBuilder
 
+analysis_exec = AnalysisExecutor(id="analysis", app_context=app_context)
+design_exec = DesignExecutor(id="design", app_context=app_context)
+yaml_exec = YamlConvertExecutor(id="yaml", app_context=app_context)
+docs_exec = DocumentationExecutor(id="documentation", app_context=app_context)
+
 workflow = (
-    WorkflowBuilder()
-    .register_executor(lambda: AnalysisExecutor(id="analysis", app_context=app_context), name="analysis")
-    .register_executor(lambda: DesignExecutor(id="design", app_context=app_context), name="design")
-    .register_executor(lambda: YamlConvertExecutor(id="yaml", app_context=app_context), name="yaml")
-    .register_executor(lambda: DocumentationExecutor(id="documentation", app_context=app_context), name="documentation")
-    .set_start_executor("analysis")
-    .add_edge("analysis", "design")
-    .add_edge("design", "yaml")
-    .add_edge("yaml", "documentation")
+    WorkflowBuilder(start_executor=analysis_exec)
+    .add_chain([analysis_exec, design_exec, yaml_exec, docs_exec])
     .build()
 )
 ```
@@ -355,7 +353,7 @@ To run processor unit tests locally (example):
 
 ```bash
 cd src/processor
-uv run --prerelease=allow python -m pytest src/processor/src/tests/unit -v
+uv run python -m pytest src/tests/unit -v
 ```
 
 ## Extending the pipeline

infra/vscode_web/codeSample.py

@@ -1,3 +1,4 @@
+from azure.ai.agents.models import ListSortOrder
 from azure.ai.projects import AIProjectClient
 from azure.identity import DefaultAzureCredential
 
@@ -7,19 +8,25 @@
 
 agent = project_client.agents.get_agent("<%= agentId %>")
 
-thread = project_client.agents.create_thread()
+thread = project_client.agents.threads.create()
 print(f"Created thread, ID: {thread.id}")
 
-message = project_client.agents.create_message(
+message = project_client.agents.messages.create(
     thread_id=thread.id,
     role="user",
     content="<%= userMessage %>"
 )
 
-run = project_client.agents.create_and_process_run(
+run = project_client.agents.runs.create_and_process(
     thread_id=thread.id,
     agent_id=agent.id)
-messages = project_client.agents.list_messages(thread_id=thread.id)
 
-for text_message in messages.text_messages:
-    print(text_message.as_dict())
+if run.status == "failed":
+    print(f"Run failed: {run.last_error}")
+else:
+    messages = project_client.agents.messages.list(
+        thread_id=thread.id, order=ListSortOrder.ASCENDING)
+
+    for message in messages:
+        if message.text_messages:
+            print(f"{message.role}: {message.text_messages[-1].text.value}")

infra/vscode_web/requirements.txt

@@ -1,3 +1,3 @@
-azure-ai-projects==1.0.0b12
+azure-ai-projects==2.1.0
 azure-identity==1.20.0
 ansible-core~=2.17.0

src/processor/pyproject.toml

@@ -5,7 +5,7 @@ description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
-    "agent-framework==1.0.0b260107",
+    "agent-framework==1.3.0",
     "aiohttp==3.13.5",
     "art==6.5",
     "azure-ai-agents==1.2.0b5",