fix: CI failures — pyupgrade, evaluator overloads, sample API, reset attr

- Apply pyupgrade: Sequence from collections.abc, remove forward-ref quotes
- Add @overload signatures to evaluator() for proper @evaluator usage
- Fix evaluate_workflow sample to use WorkflowBuilder(start_executor=) API
- Fix _workflow.py executor.reset() to use getattr pattern for pyright
- Remove unused EvalResults forward-ref string in default_factory lambda

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

Author: alliscode

python/packages/azure-ai/agent_framework_azure_ai/_foundry_evals.py

@@ -25,7 +25,8 @@
 
 import asyncio
 import logging
-from typing import TYPE_CHECKING, Any, Sequence, cast
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, cast
 
 from agent_framework._evaluation import (
     ConversationSplit,

python/packages/core/agent_framework/_evaluation.py

@@ -35,18 +35,18 @@
 import inspect
 import json
 import logging
-from collections.abc import Callable
+from collections.abc import Callable, Sequence
 from dataclasses import dataclass, field
 from enum import Enum
 from typing import (
     TYPE_CHECKING,
     Any,
     Literal,
     Protocol,
-    Sequence,
     TypedDict,
     Union,
     cast,
+    overload,
     runtime_checkable,
 )
 
@@ -425,7 +425,7 @@ class EvalResults:
     error: str | None = None
     per_evaluator: dict[str, dict[str, int]] = field(default_factory=lambda: dict[str, dict[str, int]]())
     items: list[EvalItemResult] = field(default_factory=lambda: list[EvalItemResult]())
-    sub_results: dict[str, "EvalResults"] = field(default_factory=lambda: dict[str, "EvalResults"]())
+    sub_results: dict[str, EvalResults] = field(default_factory=lambda: dict[str, EvalResults]())
 
     @property
     def passed(self) -> int:
@@ -1154,6 +1154,14 @@ def _coerce_result(value: Any, check_name: str) -> CheckResult:
     raise TypeError(msg)
 
 
+@overload
+def evaluator(fn: Callable[..., Any], /) -> EvalCheck: ...
+
+
+@overload
+def evaluator(*, name: str | None = None) -> Callable[[Callable[..., Any]], EvalCheck]: ...
+
+
 def evaluator(
     fn: Callable[..., Any] | None = None,
     *,

python/packages/core/agent_framework/_workflows/_workflow.py

@@ -347,8 +347,9 @@ async def _run_workflow_with_tracing(
                     self._state.clear()
                     # Reset all executors (clears cached messages, sessions, etc.)
                     for executor in self.executors.values():
-                        if hasattr(executor, "reset"):
-                            executor.reset()
+                        reset_fn = getattr(executor, "reset", None)
+                        if reset_fn is not None:
+                            reset_fn()
 
                 # Store run kwargs in State so executors can access them.
                 # Only overwrite when new kwargs are explicitly provided or state was

python/samples/03-workflows/evaluation/evaluate_workflow.py

@@ -15,7 +15,6 @@
 
 from agent_framework import (
     Agent,
-    AgentExecutor,
     LocalEvaluator,
     WorkflowBuilder,
     evaluate_workflow,
@@ -35,11 +34,7 @@ async def main():
     planner = Agent(model="gpt-4o-mini", instructions="You plan trips. Output a bullet-point plan.")
     executor_agent = Agent(model="gpt-4o-mini", instructions="You execute travel plans. Book the items listed.")
 
-    builder = WorkflowBuilder()
-    builder.add_executor(AgentExecutor("planner", planner))
-    builder.add_executor(AgentExecutor("booker", executor_agent))
-    builder.add_edge("planner", "booker")
-    workflow = builder.build()
+    workflow = WorkflowBuilder(start_executor=planner).add_edge(planner, executor_agent).build()
 
     # Evaluate with per-agent breakdown
     local = LocalEvaluator(is_nonempty, keyword_check("plan", "trip"))