## TL;DR
Fix this in moderation queue triage agent by acting on the exact problem first: persist the queue cursor and decisions outside the session after each batch, re-authenticate between batches rather than mid batch, and resume triage from the first undecided report, so an expired session costs one login and no decisions. Do not rerun the whole job or queue unchanged, because the same inputs produce the same failure. Prove the fix on one post, thread, report or batch first, then rerun the full scope and reconcile the counts.

```text
Session expired mid-run while triaging the moderation queue
```

## Use this when
- The operation in moderation queue triage agent fails with this exact message or symptom: Session expired mid-run while triaging the moderation queue.
- The same failure repeats on retry with unchanged inputs.
- Moderation, routing, auditing or a member facing community task is blocked until this item completes.

## Not for this skill when
- The message is an outage notice from the platform. Resolve that first, then return here if this problem remains.
- The operation completes and you only disagree with a moderation judgment or content quality. That is a policy review, not this failure.

## Steps
1. Reproduce the failure with the smallest scope that still shows it in moderation queue triage agent, and copy the full message plus the post, thread, report or member involved into the run notes. Verify: the problem is reproduced on demand with a named scope, not only seen in a log.
2. Apply the specific fix for this problem: persist the queue cursor and decisions outside the session after each batch, re-authenticate between batches rather than mid batch, and resume triage from the first undecided report, so an expired session costs one login and no decisions. Verify: the smallest failing scope now completes, or the named post, thread or report behaves as the fix predicts.
3. Check the neighbouring posts, threads, reports or members that share the same setting, rule or workflow, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in moderation queue triage agent on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts or status against the source in moderation queue triage agent so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the problem, the fix applied and the evidence of success.

## Why it happens
Queue triage runs longer than a typical session lifetime, and decisions held only in session memory vanish when the session expires near the end of the queue.

## Variant phrasings

### Session expired mid-run while triaging the moderation queue
The verbatim form searchers paste from the console, queue or report. Treat it identically: same fix, same single scope proof, then the full rerun.

### How to fix - token expired mid-run agent failed to triage the moderation queue error session expired failure
The how to phrasing for the same failure in moderation queue triage agent. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

### moderation queue triage agent troubleshooting for this failure
The symptom first phrasing used when the console hides the full message. Surface the full message first, confirm it matches the code block above, then follow the steps.

## Edge cases
- If the fix works on the small scope but the full rerun still fails on a different item, treat that item as a new instance, record its scope separately, and apply the same steps rather than widening the first fix blindly.
- If members or reports are affected in a way that cannot be undone, such as a sent digest or a deleted post, restore or notify from the audit record first, then apply the fix, and note the affected count in the run record.
- If two settings or rules could both produce this symptom, change one at a time and retest the small scope after each change, so the working fix is known rather than guessed.

Compatibility: moderation queue triage agent at current versions, plus the admin console, moderation queue or API the query names; no extra tooling beyond the source system access needed to verify counts.

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_7OUt_NO3WuhG-6u4tyt3eg