Python: [Bug]: APPROVAL_RESUME_NOT_FOUND leaves the interrupt in the thread snapshot, so the unanswerable approval card is re-offered on every connect

[antsok]

Description

Summary

When a resume is rejected with APPROVAL_RESUME_NOT_FOUND, the pending-approval registry has no entry for that interrupt and never will — the code is terminal by definition. But the thread snapshot still records the interrupt, so a client that reconnects is handed RUN_FINISHED{outcome:{type:"interrupt", …}} again, rebuilds the same card, answers it, and is rejected again.

The neighbouring APPROVAL_RESUME_CANCELLED branch already does the right thing: it calls _clear_thread_snapshot_interrupt so the resolved interrupt stops being replayed. NOT_FOUND — the more terminal of the two — does not.

In _agent_run.py on this pin, the resume-error branch computes should_clear_tool_approval_state for both codes (line ~2232), clears the tool-approval state for both (line ~2238), and then clears the snapshot interrupt only for APPROVAL_RESUME_CANCELLED (line ~2240). The helper it would need is already imported and already handles a subset of ids.

Why it is not self-limiting

Two properties turn "one rejected resume" into a thread the user cannot leave:

1. The card is rebuilt from the snapshot on every connect, so it survives reloads and replica changes — it is not client state that a refresh clears.
2. A client with an open interrupt cannot simply send a message instead. The AG-UI client refuses to start a run while pendingInterrupts is non-empty, so a surface that turns a send into a resume (any HITL client that must address open interrupts first) has no way out: the answer is rejected and the message is converted into another rejected answer.

The degrade text a host typically shows on this code — "resend your answer as a new message" — is therefore advice the protocol has made impossible to follow.

Observed in production on our AG-UI app: ten rejected resumes on one thread across four deployments and roughly two hours, after which the conversation was abandoned. The user's transcript was intact the whole time; only the interrupt was unanswerable.

Reproduction

Any path that produces APPROVAL_RESUME_NOT_FOUND while a snapshot exists will do. Two reliable ones:

1. Process/replica change. Register an approval, restart the process (the in-memory pending-approval registry is not rehydrated from the snapshot), then resume. The snapshot still carries the interrupt; the registry does not.
2. A resume consumed by a run that then dies. The entry is consumed at ingress, the run fails before applying it, and the retry finds nothing pending.

In both cases, after the NOT_FOUND run, GET /threads/{id} still returns the interrupt and the next connect() re-offers the card.

Run side by side against main @ d56e81357e5179b6f916b180c0cb34ea2e73c80b with a minimal in-memory snapshot store, the contrast is exact — the same thread, the same surfaced interrupt, only the resume status differs:

--- APPROVAL_RESUME_CANCELLED (the code that DOES clear)
  interrupt surfaced              : ['c1']
  snapshot.interrupt (after run 1): ['c1']
  resume -> RUN_ERROR code        : ['APPROVAL_RESUME_CANCELLED']
  snapshot.interrupt (after resume): CLEARED

--- APPROVAL_RESUME_NOT_FOUND (the code that does NOT)
  interrupt surfaced              : ['c1']
  snapshot.interrupt (after run 1): ['c1']
  resume -> RUN_ERROR code        : ['APPROVAL_RESUME_NOT_FOUND']
  snapshot.interrupt (after resume): ['c1']

Impact

NOT_FOUND is a rejection the user could otherwise recover from by simply continuing the conversation. Leaving the interrupt asserted converts it into a dead thread — every answer rejected, every message converted into a rejected answer — with no path back that does not involve discarding the conversation.

Prior art (checked before filing)

• Python: [Bug]: AG-UI approval resume is consumed (and the approved tool executed) before the run can fail — a post-consume failure makes the user's answer unrecoverable, and the retry is indistinguishable from a never-pending id #7458 — the resume being consumed (and the approved tool executed) before the failure. Same neighbourhood, different defect: that one is about spending the answer, this one about never being able to give it again.
• Python: [Feature]: persist AG-UI thread snapshots incrementally (and handle client disconnect), not only at run completion #7215 — persist AG-UI thread snapshots incrementally, not only at run completion. About when snapshots are written, not about retiring an interrupt that can no longer be honoured.
• Python: [Feature]: Make the AG-UI Approval State store pluggable #7082 — making the approval-state store pluggable. Would reduce how often the registry goes missing; it does not address the snapshot continuing to advertise an interrupt after a terminal rejection.

Verified against: live main @ d56e81357e5179b6f916b180c0cb34ea2e73c80b (2026-08-04T17:23Z, core 1.13.0) — installed fresh and reproduced with the stock agent_framework_ag_ui.AgentFrameworkAgent, no application wrappers of any kind.

Code Sample

Error Messages / Stack Traces

Package Versions

agent-framework-core: 1.13.0, agent-framework-ag-ui: 1.0.1

Python Version

No response

Additional Context

Suggested direction

Treat APPROVAL_RESUME_NOT_FOUND as terminal for the interrupt it names, the way APPROVAL_RESUME_CANCELLED already is: clear those ids from the thread snapshot in the same branch that clears the tool-approval state, so the next connect does not re-offer a card no registry can satisfy. The helper and the id set are both already in hand at that point.

Worth considering alongside it: a client that has just been told NOT_FOUND still holds the interrupt as pending and is blocked from sending anything. If the protocol intends NOT_FOUND to be recoverable, the rejection needs to release the client's pending state as well — otherwise the recovery it advises cannot be performed from the surface that received it.

[github-actions]

🤖 Automated triage reproduction notes (agent-authored — trust but verify)

Agent analysis

Bug is in python/packages/ag-ui/agent_framework_ag_ui/_agent_run.py at line 2247-2249. After computing should_clear_tool_approval_state for both CANCELLED and NOT_FOUND codes, the code only calls await snapshot_session.clear_interrupts(interrupt_ids=cancelled_resume_ids or None) inside an if resume_error_code == "APPROVAL_RESUME_CANCELLED" guard. The NOT_FOUND path needs the same clear_interrupts call using the resume interrupt ids. Minimal repro: register an approval interrupt with snapshot store, clear _pending_approvals, then resume — snapshot.interrupt remains non-None.

• Failing test: python/packages/ag-ui/tests/ag_ui/test_repro_7570.py
• Files examined: python/packages/ag-ui/agent_framework_ag_ui/_agent_run.py, python/packages/ag-ui/agent_framework_ag_ui/_snapshot_session.py, python/packages/ag-ui/tests/ag_ui/test_endpoint.py
• Tests run: python/packages/ag-ui/tests/ag_ui/test_repro_7570.py::test_approval_resume_not_found_clears_snapshot_interrupt
• Reported version: agent-framework-core: 1.13.0, agent-framework-ag-ui: 1.0.1
• Current version: agent-framework-core: 1.13.0, agent-framework-ag-ui: 1.0.1

[byp411426]

Hi, I would like to take this on. I see this touches Python approval-resume behavior, and the repository guidance asks external contributors to check with the Agent Framework core team first. If this issue is available and the proposed scope is appropriate, I will reproduce it against current main, add a regression test covering stale snapshot-interrupt cleanup after APPROVAL_RESUME_NOT_FOUND, and prepare a focused fix. Could a maintainer please confirm the direction and assign the issue if appropriate?

[moonbox3]

Fixed in #7594