Python: Foundry Hosted Agent Resiliency Support

[Tao Chen (TaoChenOSU)]

Motivation & Context

Add support for resilient tasks in Foundry Hosted Agent.

• For more details on resilient tasks in FHA, please visit: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/agentserver/azure-ai-agentserver-responses/docs/resilient-responses-developer-guide.md
• For more details on steerable conversation, please visit: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/agentserver/azure-ai-agentserver-responses/docs/resilient-responses-developer-guide.md#recovery--steering-surface-on-responsecontext

Also addresses #7511

Description & Review Guide

• What are the major changes?
  • Add support for resilient_background=True in ResponsesHostServer
  • Add support for steerable_conversations=True in ResponsesHostServer
  • Handle usage content now.
  • A sample showing how a workflow can be recovered after a crash (force crash locally).
  • A sample showing how an agent can be steered.
• What is the impact of these changes?
  • A new feature, no breaking changes
• What do you want reviewers to focus on?
  • The handling of workflow checkpoints

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. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/core/agent_framework
observability.py	1133	85	92%	465, 467–468, 471, 474, 477–478, 483–484, 490–491, 497–498, 505, 507–508, 511, 514, 517–518, 523–524, 530–531, 537–538, 545, 722–723, 983, 987–989, 991, 999–1000, 1004, 1048, 1050, 1061–1063, 1065–1067, 1071, 1079, 1203–1204, 1448, 1450, 1452, 1763–1764, 1881, 2034, 2076–2077, 2264, 2513–2514, 2518, 2558–2559, 2563, 2604–2607, 2648–2649, 2824, 2827, 2839, 2856, 2860–2861, 2864, 2870, 2890, 2966, 3000, 3102, 3339, 3341
packages/foundry_hosting/agent_framework_foundry_hosting
_responses.py	828	119	85%	116–118, 234, 299–300, 314, 317–318, 385, 394, 471, 503, 518–521, 585, 635, 697, 709, 725–726, 731–734, 738–740, 745, 753, 756, 767, 812, 822, 833–835, 849–851, 854, 888–891, 896, 899, 919–920, 1016, 1087–1089, 1093, 1096–1099, 1103–1105, 1110–1114, 1118–1120, 1127–1128, 1131–1134, 1140, 1143–1149, 1159, 1165, 1169, 1193, 1202–1203, 1207, 1449, 1461, 1913–1914, 1918, 1963, 1965, 1967, 1969, 1973, 1981, 1984–1988, 1990, 2000, 2004, 2049, 2051, 2053–2056, 2064, 2066
_state_store.py	124	0	100%
TOTAL	48071	4494	90%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
9710	36 💤	0 ❌	0 🔥	2m 36s ⏱️

[Tao Chen (TaoChenOSU)]

#7809 is a follow up that requires more effort.