Python: omit failed Foundry turns from conversation chat history

[Shikhar Goel (sgoel2be24-cyber)]

Motivation & Context

When a hosted Foundry agent is used with conversation_id, a failed turn still stored its input items on the agentserver response/conversation store. The next request on that conversation replayed them via get_history(). Azure OpenAI does not keep failed input on the conversation.

Fixes #7630

Description & Review Guide

• Let ResponsesAgentServerHost resolve and validate its configured/default response store before wrapping it, preserving hosted and local persistence defaults plus the resilient-background guard.
• For synchronous non-background requests, determine the terminal result before the provider's initial create so failed input items never enter conversation history.
• Keep existing response updates atomic at the provider level instead of using delete-then-create.
• Reverted the earlier “skip MAF session persist on failure” change; that was the wrong store.
• Tests in python/packages/foundry_hosting/tests/test_responses.py cover the HTTP conversation repro, provider behavior, default persistent storage, and the resilience guard.

Please focus on: failed synchronous turns stay out of get_history(), successful turns still persist, non-conversation runs are unchanged, and the base host's storage behavior is preserved.

Related Issue

Fixes #7630

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change.

Assistance: drafted with an AI coding agent and reviewed before opening.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[Shikhar Goel (sgoel2be24-cyber)]

@microsoft-github-policy-service agree

[Chinedum Echeta (cecheta)]

Unfortunately this doesn't fix the issue, as the problem is that the messages get saved to the chat history, not the session.

[Shikhar Goel (sgoel2be24-cyber)]

You're right — the first commit skipped the wrong store.

The agentserver response provider was persisting input items for failed turns, so the next request on the same conversation replayed them via chat history (get_history()), not the MAF session.

24ebe8b wraps the response store so failed turns persist without input items (including the in_progress → failed update path). A follow-up request on the same conversation no longer sees the bad function_call_output. Tests cover both the store wrapper and the HTTP conversation repro from the issue.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.