Sample proposal: reliable multi-agent handoffs with checkpoints and safe retries
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Quiet
- Tech stack
- python
- Domain
- backend-api-design, distributed-systems, testing
Research direction
Start by reviewing the existing samples under 07.Workflow and the repository's multi-agent routing, concurrent workflow, MCP, and tracing examples. Confirm the preferred language and placement with maintainers before implementation. Done means the sample and tests demonstrate single admission, durable resume, ambiguous-result handling without replay, explicit known-failure retry, and the stated evidence distinction.
Written by the indexing model from the issue text.
Description
Why
The repository already demonstrates multi-agent routing, concurrent workflows, MCP, and tracing. A useful production-oriented addition would cover a harder failure mode: a worker completes an external action, but its response is lost. A coordinator that treats this as an ordinary failure can retry the handoff and duplicate the action.
Proposed sample
Add a small, provider-neutral multi-agent workflow (under 07.Workflow, or another maintainer-preferred location) with a coordinator, two competing workers, a mock destination, and a reliability-sidecar boundary:
- The coordinator derives a stable workflow/action key and writes a shared checkpoint before handoff.
- Two workers race to claim the same duplicate-sensitive action; atomic admission allows only one to execute it.
- The sample injects a timeout after the mock destination records the result but before the worker returns.
- Recovery treats the result as ambiguous, reads back the destination, records evidence, and resumes without replaying the action.
- A verifier advances the checkpoint only after evidence is present and reports the proof scope honestly.
The output/tests should show:
- two contenders, one admitted execution, and one destination record;
- restart/resume from a durable checkpoint;
- no automatic retry of an ambiguous result;
- a retry only after an explicit known-failure policy; and
- the distinction between caller-reported evidence and independently verified proof.
Portability
The sample could define a minimal ReliabilityBackend protocol (claim/admit, checkpoint, transition, status) with a deterministic local adapter for tests. A remote MCP adapter would be optional, so the pattern is not tied to a vendor. Agent Enhancer Utilities is one free, no-auth reference implementation, but the sample would remain runnable without it and document the semantics rather than a product.
No real email, ticket, payment, or other external side effect is needed; a counted mock sink makes the invariant testable.
If this fits the samples roadmap, I can prepare a focused PR after guidance on preferred language (Python, .NET, or both) and placement. I will not open one before maintainer confirmation.
- Dominant language
- Jupyter Notebook
- Stars
- 384
- Forks
- 150
- PR merge metrics
- No merged PRs in 30d
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- No pull request template
- No contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from microsoft/Agent-Framework-Samples
-
Difficulty 2/5 1-3 hours Newbie friendliness 55/100
-
Difficulty 3/5 1-2 days Newbie friendliness 68/100
-
GHModelAI - DEVUI does not display outputsPossibly taken @ilia-sokolov claimed this 76 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 48/100
All issues in microsoft/Agent-Framework-Samples
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Maintainers usually reply within 1 day
-
friction
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
kentcdodds/kody#3263 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
PolicyEngine/policyengine-us#10073 ·
Maintainers usually reply within 2 days
-
bug release:v5.56
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
Jason-Vaughan/TangleClaw#2270 ·
Maintainers usually reply within 1 day
-
area:jobads-cv BE mvp P2
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
klasolsson81/jobbliggaren#2099 ·
Maintainers usually reply within 1 day