Python: include checkpoint_id on AG-UI interrupt metadata (#8150) by FOWEPJF255 · Pull Request #8163 · microsoft/agent-framework

lsmlhi_25 (FOWEPJF255) · 2026-09-08T17:45:26Z

Motivation & Context

AG-UI workflow interrupts need a durable pause checkpoint_id so multi-worker clients can resume via forwardedProps.checkpoint_id without a side-channel lookup (Option A from #8150).

Description & Review Guide

What are the major changes?
- Attach the pause checkpoint_id to each interrupt's metadata.agent_framework when AG-UI workflow runs finish with interrupts and checkpoint storage is active.
- Prefer this runner's last-saved pause checkpoint over shared get_latest(workflow_name=...) (avoids cross-owner races / stale ids).
- Resolve builder-configured checkpoint storage via the workflow runner when run_workflow_stream does not pass checkpoint_storage.
- Skip storage work when interrupts is empty; remove the unused checkpoint_id kwarg on _workflow_interrupt_metadata.
What is the impact of these changes?
- Clients can round-trip the pause checkpoint id from interrupt metadata for durable resume across workers.
What do you want reviewers to focus on?
- Correctness of pause-id selection vs shared get_latest, builder-only storage path, and empty-interrupt short-circuit.

Related Issue

Fixes #8150

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) 鈥?a workflow keeps the label and title prefix in sync automatically.

…8150) Attach the pause workflow checkpoint id to RUN_FINISHED interrupt metadata.agent_framework so multi-worker clients can resume via forwardedProps.checkpoint_id without a side channel.

Copilot

🟡 Changes recommended

Checkpoint selection can advertise a stale or different request owner’s checkpoint ID.

Once you've addressed the issues Copilot identified, you can request another Copilot review.

Pull request overview

Adds checkpoint IDs to AG-UI workflow interrupt metadata for durable multi-worker resume.

Changes:

Resolves and attaches pause checkpoint IDs to interrupts.
Adds helper and checkpoint-resume coverage.

File summaries

File	Description
`_workflow_run.py`	Adds checkpoint lookup and interrupt metadata enrichment.
`test_workflow_run.py`	Tests attachment and checkpoint ID propagation.

Review details

Files reviewed: 2/2 changed files
Comments generated: 3
Review effort level: Balanced

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

…oft#8150)

lsmlhi_25 (FOWEPJF255) · 2026-09-09T02:26:24Z

Addressed review feedback:

Stop using shared get_latest(workflow_name=...) (races across owners / stale ids). Prefer this runner's _previous_checkpoint_id and only advertise it when the checkpoint's pending request set covers the interrupt ids.
Resolve builder-configured storage via the workflow runner when run_workflow_stream does not pass checkpoint_storage.
Skip storage work when interrupts is empty; remove the unused checkpoint_id kwarg on _workflow_interrupt_metadata.
Added regression tests for competing shared latest + builder-only storage.

Evan Mattson (moonbox3) · 2026-09-09T03:01:43Z

lsmlhi_25 (@FOWEPJF255):

Please update the PR body to use our approved template: https://github.com/microsoft/agent-framework/blob/main/.github/pull_request_template.md
Per our contributing guidelines, please respond to all open PR comments as to whether they're addressed or not. Then resolve the threads once done.
Please also fix the failing code quality checks.

lsmlhi_25 (FOWEPJF255) · 2026-09-09T07:15:20Z

Evan Mattson (@moonbox3) Thanks 鈥?addressed your checklist:

PR body updated to the approved template.
Replied on each review thread and resolved them.
Pushed a follow-up for the failing code quality checks: ruff I001 (import blank line) and ty ignores on the new yield_output("done") test helpers.

Move pause-checkpoint selection into Workflow and require a run-scoped baseline so leftover runner ids are not advertised across runs.

lsmlhi_25 (FOWEPJF255) · 2026-09-09T09:23:54Z

Evan Mattson (@moonbox3) Follow-up for the run-scoped / core-helper review:

Workflow.get_last_checkpoint_id() + Workflow.resolve_pause_checkpoint_id(...) in core (storage precedence, pending-request coverage, run-scoped baseline filter).
AG-UI captures the baseline before workflow.run() and no longer digs into Runner private fields for pause-id selection.
Regression tests in core test_pause_checkpoint_resolve.py and AG-UI run-scoped coverage.

Commit: 68f5abe.

Unblocks Package Checks / merge-gatekeeper on PR microsoft#8163.

- Workflow captures run baseline / restored id inside run(); resolve uses them so callers need not thread baseline_checkpoint_id. - Exclude restored checkpoint from pause candidates after resume. - Drop issue reference in docstring; emit RUN_FINISHED via existing _build_run_finished_event after attaching pause id. - Move core pause-resolve coverage into test_workflow.py (no new test file).

LI (ktz03) · 2026-09-11T09:33:03Z

Left a follow-up into your branch for the open Eduard van Valkenburg (@eavanvalkenburg) / Evan Mattson (@moonbox3) threads:

fix(ag-ui): address #8163 review on pause checkpoint ownership FOWEPJF255/agent-framework#2 (ktz03:fix/8163-review-followup)

Highlights:

Workflow owns run baseline + restored id inside
un(); AG-UI no longer threads �aseline_checkpoint_id / resume known_checkpoint_id`n- Restored checkpoint excluded from pause candidates after resume
Docstring no longer cites the issue; RUN_FINISHED goes through existing _build_run_finished_event`n- Core pause-resolve tests moved into est_workflow.py (dedicated test file removed)

Feel free to merge #2 or cherry-pick �58e11f.

…ip (#2) - Workflow captures run baseline / restored id inside run(); resolve uses them so callers need not thread baseline_checkpoint_id. - Exclude restored checkpoint from pause candidates after resume. - Drop issue reference in docstring; emit RUN_FINISHED via existing _build_run_finished_event after attaching pause id. - Move core pause-resolve coverage into test_workflow.py (no new test file).

lsmlhi_25 (FOWEPJF255) · 2026-09-11T13:36:33Z

Merged the pause-checkpoint ownership follow-up on the PR branch (FOWEPJF255#2). Ready for another maintainer pass.

lsmlhi_25 (FOWEPJF255) · 2026-09-13T09:35:41Z

All open review threads from Evan Mattson (@moonbox3) / Eduard van Valkenburg (@eavanvalkenburg) are addressed on the PR head (d42a8b3, via FOWEPJF255#2):

Workflow owns run baseline + excludes restored checkpoint from pause candidates
AG-UI reuses _build_run_finished_event (no extra helper / issue link in docstring)
Core tests live in test_workflow.py (no dedicated bug-fix test file)

Ready for another look when you have a moment.

lsmlhi_25 (FOWEPJF255) · 2026-09-13T09:36:24Z

All open review threads from Evan Mattson (@moonbox3) / Eduard van Valkenburg (@eavanvalkenburg) are addressed on the PR head (d42a8b3, via FOWEPJF255#2):

Workflow owns run baseline + excludes restored checkpoint from pause candidates
AG-UI reuses _build_run_finished_event (no extra helper / issue link in docstring)
Core tests live in test_workflow.py (no dedicated bug-fix test file)

Ready for another look when you have a moment.

Python: include checkpoint_id on AG-UI interrupt metadata (microsoft#…

5c44073

…8150) Attach the pause workflow checkpoint id to RUN_FINISHED interrupt metadata.agent_framework so multi-worker clients can resume via forwardedProps.checkpoint_id without a side channel.

Copilot AI balanced review requested due to automatic review settings September 8, 2026 17:45

lsmlhi_25 (FOWEPJF255) requested review from chetantoshniwal, Eduard van Valkenburg (eavanvalkenburg), Giles Odigwe (giles17) and Evan Mattson (moonbox3) as code owners September 8, 2026 17:45

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 8, 2026 17:45 — with GitHub Actions Inactive

agent-framework-automation Bot added the python Usage: [Issues, PRs], Target: Python label Sep 8, 2026

Copilot started reviewing on behalf of lsmlhi_25 (FOWEPJF255) September 8, 2026 17:46 View session

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 8, 2026 17:46 — with GitHub Actions Inactive

Copilot AI reviewed Sep 8, 2026

View reviewed changes

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Evan Mattson (moonbox3) reviewed Sep 9, 2026

View reviewed changes

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Python: Prefer runner pause checkpoint over shared get_latest (micros…

8e36bd4

…oft#8150)

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 9, 2026 02:26 — with GitHub Actions Inactive

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 9, 2026 05:10 — with GitHub Actions Inactive

Python: Fix ag-ui lint and ty ignores for microsoft#8150 tests

c6f10d8

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 9, 2026 07:15 — with GitHub Actions Inactive

Evan Mattson (moonbox3) reviewed Sep 9, 2026

View reviewed changes

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Python: Core resolve_pause_checkpoint_id for AG-UI (microsoft#8150)

68f5abe

Move pause-checkpoint selection into Workflow and require a run-scoped baseline so leftover runner ids are not advertised across runs.

lsmlhi_25 (FOWEPJF255) requested review from Tao Chen (TaoChenOSU) and Jose Alvarez (jpalvarezl) as code owners September 9, 2026 09:23

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 9, 2026 09:23 — with GitHub Actions Inactive

fix(python): resolve pyright failures in pause checkpoint lookup

d4b60eb

Unblocks Package Checks / merge-gatekeeper on PR microsoft#8163.

lsmlhi_25 (FOWEPJF255) temporarily deployed to github-app-auth September 9, 2026 17:11 — with GitHub Actions Inactive

Evan Mattson (moonbox3) reviewed Sep 10, 2026

View reviewed changes

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

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

Eduard van Valkenburg (eavanvalkenburg) reviewed Sep 10, 2026

View reviewed changes

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py Outdated

Comment thread python/packages/ag-ui/agent_framework_ag_ui/_workflow_run.py

Comment thread python/packages/core/tests/workflow/test_pause_checkpoint_resolve.py Outdated

LI (ktz03) mentioned this pull request Sep 11, 2026

fix(ag-ui): address #8163 review on pause checkpoint ownership FOWEPJF255/agent-framework#2

Merged

lsmlhi_25 (FOWEPJF255) requested review from SergeyMenshykh, Roger Barreto (rogerbarreto) and westey (westey-m) as code owners September 11, 2026 13:36

lsmlhi_25 (FOWEPJF255) deployed to github-app-auth September 11, 2026 13:36 — with GitHub Actions Active

Uh oh!

Conversation

lsmlhi_25 (FOWEPJF255) commented Sep 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Motivation & Context

Description & Review Guide

Related Issue

Contribution Checklist

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

🟡 Changes recommended

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 9, 2026

Uh oh!

Evan Mattson (moonbox3) commented Sep 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 9, 2026

Uh oh!

Uh oh!

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 9, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

LI (ktz03) commented Sep 11, 2026

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 11, 2026

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 13, 2026

Uh oh!

lsmlhi_25 (FOWEPJF255) commented Sep 13, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

lsmlhi_25 (FOWEPJF255) commented Sep 8, 2026 •

edited

Loading

Evan Mattson (moonbox3) commented Sep 9, 2026 •

edited

Loading