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

Description & Review Guide

• What are the major changes?
  • Add support for resilient_background=True in ResponsesHostServer
  • Add support for steerable_conversations=True in ResponsesHostServer
  • 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/foundry_hosting/agent_framework_foundry_hosting
_responses.py	759	111	85%	111–113, 174–175, 189, 192–193, 260, 269, 346, 378, 393–394, 458, 508, 572, 584, 600–601, 606–609, 617–618, 629, 668–671, 686, 732–735, 740, 743, 763–764, 1135, 1147, 1599–1600, 1604, 1649, 1651, 1653, 1655, 1659, 1667, 1670–1674, 1676, 1686, 1690, 1737–1742, 1746–1747, 1755–1761, 1791–1792, 1794–1795, 1797, 1802, 1810–1811, 1813, 1818–1822, 1824, 1831–1832, 1834–1835, 1841, 1843–1847, 1857, 1863, 1887, 1893, 1899, 1901, 1903–1906, 1914, 1916
_state_store.py	124	0	100%
TOTAL	46824	4377	90%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
9459	36 💤	0 ❌	0 🔥	2m 27s ⏱️

[Copilot]

Pull request overview

Adds resilient background recovery for Python Foundry-hosted workflow agents and a countdown sample demonstrating the feature.

Changes:

• Adds workflow checkpoint and response-stream recovery integration.
• Refactors response handling and cancellation plumbing.
• Adds a resilient hosted-agent sample and deployment assets.

Reviewed changes

Copilot reviewed 10 out of 12 changed files in this pull request and generated 9 comments.

Show a summary per file

File	Description
_responses.py	Implements resilient workflow recovery and shared response handling.
test_responses.py	Updates tests for the refactored handler signature.
foundry_hosting/README.md	Minor formatting correction.
Sample main.py	Defines the resilient countdown workflow.
Sample README.md	Documents running and invoking the sample.
Sample requirements.txt	Declares framework dependencies.
Sample Dockerfile	Packages the sample container.
Sample agent.yaml	Configures the hosted agent.
Sample agent.manifest.yaml	Defines deployment metadata and resources.
Sample .env.example	Lists required environment variables.
Sample .dockerignore	Excludes local Python artifacts and secrets.

Suppressed comments (1)

python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py:643

• The previous implementation rejected an unknown previous_response_id; this refactor silently starts a fresh workflow when no checkpoint is found. That breaks response chaining by returning an unrelated successful response instead of reporting the missing predecessor. Restore the missing-checkpoint validation.

                latest_checkpoint = await restore_checkpoint_storage.get_latest(workflow_name=self._agent.workflow.name)
                if latest_checkpoint is not None:
                    latest_checkpoint_id = latest_checkpoint.checkpoint_id

---

💡 Add a code-review agent skill for context-aware, tailored reviews. Learn more in the docs.

[github-actions]

MAF Automated Review — Iteration 1

Result: Findings reported
Scope: full PR (18 commit(s)): ff8450b9fe0f, 4cf73d533ca7, 14cf002f7a00, 3df40fd8b17f, 10ab3c334565, 8838c1ede111, 649443c48221, 19303b75a6f4, 95f0ac3181f5, 8d038e37f6c9, 828e5df4263c, 172a5289eef1, 6db0df3f6fc6, 7ac2a9bcf86b, df0d18152f5a, 8b5da3a5e724, b0ac69de72e0, d9e6d5a49eb8
Model: gpt-5.6-sol

Overview

The review found 6 verified inline finding(s).

Reviewed the supplied pull-request change set across correctness, security/reliability, architecture, and failure behavior.
6 verified findings remained after source verification (3 high, 3 medium) across 3 files. Details are attached to the affected lines below.

Affected areas: python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py, python/samples/04-hosting/foundry-hosted-agents/responses/resilient_long_running_workflow/main.py, python/samples/04-hosting/foundry-hosted-agents/responses/resilient_long_running_workflow/requirements.txt

[Tao Chen (TaoChenOSU)]

An issue discovered while working on this feature: #7677

[github-actions]

MAF Automated Review — Iteration 2

Result: Findings reported
Scope: 4 net-new commit(s): 9b8d5f4b85da, b1357a67ce93, 3825d3bd78da, cb550c0ea82b
Model: gpt-5.6-sol

Overview

The update adds explicit configuration guards, continuation validation, checkpoint-event propagation, and a dedicated recovery stream, addressing several earlier failure modes. Cancellation checks and output balancing also improve lifecycle handling. However, response snapshots are still paired with the checkpoint preceding the update being persisted, so a crash can replay already-recorded output and side effects.

Reviewed the supplied incremental change set across correctness, security/reliability, architecture, and failure behavior.
1 verified finding remained after source verification (1 high) across 1 file. Details are attached to the affected lines below.

Affected areas: python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py