## TL;DR
Break the loop by recording the failure reason for this recording, removing it from the automatic retry queue after the agreed attempt limit, and surfacing it as a manual repair item so other recordings summarize normally. Start with the agent queue showing the same Aircall recording repeatedly, its failure reason, and the attempt count so far, work on one affected call, record, or run first, and prove the fix there before running the full set. Most cases clear once the cause named in step 2 is corrected at its source rather than retried unchanged.

```text
agent loop detected repeatedly summarizing the same failed Aircall recording
```

## Use this when
- You see this exact message or symptom: agent loop detected repeatedly summarizing the same failed Aircall recording
- One run, record, call, or object is affected and you can name it
- A retry without changing anything reproduces the same result

## Not for this skill when
- The system fails with a different message and none of the signals here appear
- Nothing has failed yet and you are doing first time setup or general planning
- Every service from this vendor is down for all users, which is a vendor outage to wait out first

## Steps
1. Reproduce the failure once using the agent queue showing the same Aircall recording repeatedly, its failure reason, and the attempt count so far, and record the time, the workspace or account, and the one item it names. Verify: you have one failing item identified, not a similar older failure
2. Inspect whether the failure is identical on every attempt and whether any attempt limit or failure record exists. Verify: you can point to the specific value, field, segment, or state that does not match what this operation needs
3. Apply the fix at that source: break the loop by recording the failure reason for this recording, removing it from the automatic retry queue after the agreed attempt limit, and surfacing it as a manual repair item so other recordings summarize normally. Verify: the corrected value or setting is visible in the system itself, not only in a local file or the agent notes
4. Re-run the original operation on the single affected item first. Verify: that one item completes with no trace of the failure described above, and the recording sits in a manual repair list with its reason and the queue moves on to the next recording
5. Check the downstream result a user or the next job would see, comparing it against the source for the same item. Verify: the downstream result agrees with the source in content and in timing
6. Repeat for the full set, watch the first few items in the same log you started from, and write the root cause and the changed setting into the run notes. Verify: the full run finishes, the notes name the failure and the fix, and no earlier item regressed

## Variant phrasings
### agent loop detected repeatedly summarizing the same failed Aircall recording
The subject-first phrasing of the same failure. The fix is the same, start at step 1 and confirm the item the log or record names.
### Tool-first phrasing of this failure
The phrasing searchers use once they know which system raised it. It is the same underlying problem, not a separate bug.
### Why does this keep happening after a retry
The repeat-occurrence phrasing. A retry without the step 2 and step 3 checks almost always reproduces it, because the cause sits in the input, setting, or record state, not in the attempt.

Compatibility: Agent summary queues for Aircall recordings, at current versions

## Why it happens
A recording that fails deterministically, such as a corrupt or missing file, will fail forever, and a queue with no attempt limit spends all its runs proving that again.

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_lAPK3uTYi85LYQwQ_GnttA