auth token expired mid-run agent failed to summarize pulse survey comments into themes error session expired failure

TL;DR

Fix this in pulse survey comment summarisation agent by acting on the exact problem first: save each finished batch of themes to a run file outside the session as the agent goes, refresh the sign in session between comment batches, and on expiry sign in again and resume with the first batch that has no saved themes so finished work survives. Do not rerun the same survey, report or export unchanged, because the same inputs produce the same failure. Prove the fix on one survey, team or department first, then rerun the full scope and reconcile the results.

auth token expired mid-run agent failed to summarize pulse survey comments into themes error session expired failure

Use this when

• The operation in pulse survey comment summarisation agent fails with this exact problem: auth token expired mid-run agent failed to summarize pulse survey comments into themes error session expired failure.
• The same failure repeats on retry with unchanged inputs.
• A survey launch, results dashboard, manager report or action plan is blocked until this is resolved.

Not for this skill when

• The notice is a platform outage from the vendor. Resolve that first, then return here if this problem remains.
• The operation completes and you only disagree with an interpretation call such as which driver to prioritise. That is a people analytics judgement, not this failure.

Steps

1. Reproduce the failure on one named survey, team or department in pulse survey comment summarisation agent and record the full problem text plus the survey, team or period involved. Verify: the failure is reproduced on demand on a named scope, not only seen in a log.
2. Apply the specific fix for this problem: save each finished batch of themes to a run file outside the session as the agent goes, refresh the sign in session between comment batches, and on expiry sign in again and resume with the first batch that has no saved themes so finished work survives. Verify: the single failing survey, team or department now behaves as the fix predicts, or the corrected value is visible on the record.
3. Check neighbouring surveys, teams or departments that share the same distribution list, roster sync or dashboard, because this class of failure rarely affects only one group. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in pulse survey comment summarisation agent on the previously failing scope, watching for the same problem rather than assuming success from a quiet log. Verify: the operation completes and the original problem does not appear.
5. Compare the result against the source of truth, the raw response record, the HR roster record or the survey platform record, so a silent partial success is caught. Verify: values match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the survey run log so the next occurrence is recognised immediately. Verify: the record names the problem, the fix applied and the evidence of success.

Variant phrasings

auth token expired mid-run agent failed to summarize pulse survey comments into themes error session expired failure

The verbatim form searchers paste from the console, report or run log. Treat it identically: same fix, same single group proof, then the full rerun.

How to fix - auth token expired mid-run agent failed to summarize pulse survey comments into themes error session expired failure

The how to phrasing for the same failure in pulse survey comment summarisation agent. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

pulse survey comment summarisation agent troubleshooting for this failure

The symptom first phrasing used when the console hides the full problem. Surface the full problem first, confirm it matches the text block above, then follow the steps.

Why it happens

Theming a full survey touches comment batches in sequence and outlives a short sign in session, and themes held only in session memory vanish on expiry, causing repeated work and gaps in the theme set.

Edge cases

• The survey was reopened, the roster was resynced or a team was restructured after the failing run started. Refresh the survey state and reapply the fix against the current values, not the values from the failed run.
• The single group proof passes but the full rerun still fails on other groups. Treat each remaining failure as its own scope, because a shared distribution list or dashboard can hide more than one cause.
• The source systems disagree on the correct value. The raw response record governs response counts, the HR roster governs who was invited, and the platform record governs what was sent or shown; record which source won and why.

Compatibility: pulse survey comment summarisation agent at current versions, plus the survey platform, roster or reporting tool the query names; no extra tooling beyond access to the source records needed to verify results.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_tZYM74GuqimbB3fRs4zj6g