Python: Fix duplicate messages in Handoff workflow

[LEDazzio01]

Motivation and Context

Fixes #4695

When using HandoffBuilder with AzureOpenAIChatClient (or any Chat Completions-based client), the refund agent's conversation history shows every message duplicated. The user reports 18 messages where only 9 are expected.

Root Cause

HandoffBuilder._clone_chat_agent() preserves the original agent's context_providers, including InMemoryHistoryProvider. The HandoffAgentExecutor manages its own conversation state via _full_conversation and _cache. When the executor calls agent.run(self._cache, session=self._session):

1. _cache already contains the full conversation from _full_conversation
2. InMemoryHistoryProvider.before_run() loads all previously stored messages from session state into context_messages
3. session_messages = context_messages + input_messages → the entire conversation appears twice

This is the same root cause identified in #4411. PR #4412 proposed the same fix but was closed without merging.

Description

• Filter out BaseHistoryProvider instances from the cloned agent's context_providers in _clone_chat_agent(), since the executor already manages conversation history
• Add a no-op InMemoryHistoryProvider placeholder (load_messages=False, store_inputs=False, store_outputs=False) to prevent the agent from auto-injecting a default one at runtime
• Add a regression test (test_no_duplicate_messages_after_handoff_and_resume) that verifies no duplicate messages are sent to the agent after a handoff + user reply sequence, using a CapturingChatClient that records the exact messages passed to each API call

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the Contribution Guidelines
• All unit tests pass, and I have added new tests where possible
• Is this a breaking change? No

[Copilot]

Pull request overview

Fixes duplicated conversation history being sent to Chat Completions-based agents in HandoffBuilder workflows by preventing history providers from re-injecting previously stored messages, and adds a regression test to validate the behavior.

Changes:

• Strip BaseHistoryProvider instances from cloned handoff agents’ context_providers and add a no-op InMemoryHistoryProvider placeholder to prevent default history auto-injection.
• Add a regression test using a CapturingChatClient to ensure messages are not duplicated after a handoff + resume.
• Add two contribution log markdown files under contribution-logs/.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 4 comments.

File	Description
python/packages/orchestrations/agent_framework_orchestrations/_handoff.py	Prevents duplicate message injection by filtering history providers during agent cloning.
python/packages/orchestrations/tests/test_handoff.py	Adds a regression test that inspects messages passed to the specialist client after resume.
contribution-logs/2026-03-14.md	Adds a contribution status log entry (appears unrelated to handoff fix).
contribution-logs/2026-03-15.md	Adds a contribution status log entry (appears unrelated to handoff fix).

---

You can also share your feedback on Copilot code review. Take the survey.

[LEDazzio01]

Thanks for the review, Copilot! All feedback has been addressed in the rebased commit:

1. Redundant guard simplified — The if not any(isinstance(p, BaseHistoryProvider) ...) check was removed. The no-op InMemoryHistoryProvider is now unconditionally appended after filtering, since filtered_providers will never contain a BaseHistoryProvider at that point.

2. Test assertions improved — The regression test now uses structural fingerprints (m.role, tuple((c.type, c.text) for c in m.contents)) instead of comparing .text values with set(...). This correctly handles non-text messages and avoids false-failing on legitimately identical text.

3. Unrelated files removed — The contribution-logs/ files have been removed from this branch to keep the PR focused on the handoff fix.