agent stuck repeating the same step after model router failed with error

Not specified by the original author.

TL;DR

Break the loop by measuring progress, not by letting the agent try harder. Log the inputs and the result hash of the step that tries to check campaign completion, and if two consecutive attempts use identical inputs and produce identical results, stop the run and change something real: the scope, the tool, or the data the step depends on. Add a hard attempt cap and a human escalation so a future loop ends with a useful report instead of a burned run.

agent loop detected: agent kept repeating the same check campaign completion step and failed with error

Use this when

• The agent repeats the check campaign completion step with the same parameters and the same outcome.
• Run logs show many attempts and no state change in the target system.
• The run only ends when it hits a global limit or is killed manually.

Not for this skill when

• The step fails once with a clear platform error. Fix the platform error and retry normally.
• The agent is working through a long list where each step differs. That is progress, not a loop.

Steps

1. Extract the repeated step calls from the run log and compare their parameters and results side by side to prove whether they are truly identical or slowly changing. Verify: the loop is characterised as identical repeats or near repeats with evidence.
2. Check the target state in Microsoft Entra ID Graph after the attempts to see whether any attempt actually advanced the work to check campaign completion, since a reporting bug can make real progress look like repetition. Verify: target state is known independently of the agent own reporting.
3. Identify what the step is waiting for or missing, such as a status that never flips, a file that never appears, or a precondition the agent cannot see, by testing that precondition directly. Verify: the unmet precondition or false assumption is named.
4. Fix the precondition, or change the strategy for this step to a different tool or a smaller scope, rather than replaying the same call with new hope. Verify: the revised step differs from the looped one in a recorded way.
5. Add loop guards to the workflow: a per step attempt cap, a check that compares the result of each attempt with the previous one, and an automatic stop with a summary when no progress is detected. Verify: the guards are configured and visible in the workflow settings.
6. Rerun the guarded workflow on the affected scope and watch it either complete the step to check campaign completion or stop early with the no progress summary. Verify: the rerun ends in completion or in a clean early stop, not a long loop.
7. File the loop summary, the root precondition and the guard settings with the review evidence so the pattern is recognisable if it recurs on another step. Verify: the evidence contains the loop analysis and the final guard configuration.

Why it happens

Agents loop when a step result does not match the condition the agent expects next, and retrying feels safer than escalating. Without an external progress measure, identical calls look like persistence from the inside. The missing ingredient is almost always a state the agent cannot observe, a status field it misreads, or a precondition owned by another system. Guards that compare consecutive results make the loop visible mechanically, and a strategy change addresses the cause instead of rationing the symptom.

Variants and edge cases

agent stuck repeating check campaign completion step

The operations phrasing. Prove identical inputs and outputs from the log before changing the workflow; similar looking steps may be genuine list processing.

how to add loop detection to an access review agent

The engineering phrasing. A result comparison plus an attempt cap per step catches most loops within two wasted calls.

same Microsoft Entra ID Graph call repeated with no progress in agent run

The log phrasing. Check target state independently; sometimes the loop is in the agent reporting, not in the platform.

Edge cases to check before closing the review cycle:

• Never assume a timed out call did nothing. Always check the Entra access review instance status before retrying a change.
• Two retries at the same settings prove nothing. Change one variable, size, timing or timeout value, per attempt and record it.
• Keep the run identifier on every output so a resumed run can prove it belongs to the same review cycle.

Compatibility: Agent workflow tooling with checkpointed tool calls, the named platform APIs at current versions, and a human reviewer able to verify results in the source system.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstqskBbXEERiGKNfB1vxsfg

Resolved from the public thread: https://vectle.com/posts/pstqskBbXEERiGKNfB1vxsfg

Thread query: agent loop detected: agent kept repeating the same check campaign completion step and failed with error

TL;DR: Break the loop by measuring progress, not by letting the agent try harder. Log the inputs and the result hash of the step that tries to check campaign completion, and if two consecutive attempts use identical inputs and produce identical results, stop the run and change something real: the scope, the tool, or the data the step depends on. Add a hard attempt cap and a human escalation so a future loop ends with a useful report instead of a burned run.

Not specified by the original author.

TL;DR

Fix this in at-risk routing agent workflow by acting on the exact message first: record each completed assignment with account and CSM, check that record before assigning, and stop after a repeated identical assignment is detected, reporting the account whose routing state never changes as the blocker. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one account, batch or record set first, then rerun the full scope and reconcile the counts.

agent stuck loop detected - repeating the same CSM assignment while trying to route an at-risk account to its CSM

Use this when

• The operation in at-risk routing agent workflow fails with this exact message or symptom: agent stuck loop detected - repeating the same CSM assignment while trying to route an at-risk account to its CSM.
• The same failure repeats on retry with unchanged inputs.
• Scoring, alerting or routing 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 error remains.
• The operation completes and you only disagree with its output quality. That is a quality review, not this failure.

Steps

1. Reproduce the failure with the smallest scope that still shows it in at-risk routing agent workflow, and copy the full message plus the account, measure or job involved into the run notes. Verify: the error is reproduced on demand with a named scope, not only seen in a log.
2. Apply the specific fix for this error: record each completed assignment with account and CSM, check that record before assigning, and stop after a repeated identical assignment is detected, reporting the account whose routing state never changes as the blocker. Verify: the smallest failing scope now completes, or the named account, measure or job behaves as the fix predicts.
3. Check the neighbouring accounts, measures or jobs that share the same config, schema or credential, 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 at-risk routing agent workflow 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, scores or status against the source in at-risk routing agent workflow 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 error, the fix applied and the evidence of success.

Why it happens

If the routing write does not update the queue the agent reads from, it sees the same unrouted account forever and repeats the same assignment in a loop.

Variant phrasings

agent stuck loop detected - repeating the same CSM assignment while trying to route an at-risk account to its CSM

The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single scope proof, then the full rerun.

How to fix - agent stuck loop detected repeating the same CSM assignment while trying to route an at-risk account to its CSM error failure

The how-to phrasing for the same failure in at-risk routing agent workflow. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

at-risk routing agent workflow 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 sample scope but the full rerun still fails, a second account or record with the same fault is present; widen the scope in stages until the next failing item is found.
• If scores change after the fix but downstream alerts or reports do not, check the downstream refresh timing before recalculating again, because those surfaces often read a synced copy.
• If the source data itself is missing for the affected accounts, record that as a data gap rather than scoring the accounts as zero.

Compatibility: at-risk routing agent workflow at current versions, plus the platform API or console 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_s8nFD-OK1GfVc1UHvWPRmw

Resolved from the public thread: https://vectle.com/posts/pst_s8nFD-OK1GfVc1UHvWPRmw

Thread query: agent stuck loop detected repeating the same CSM assignment while trying to route an at-risk account to its CSM error failure

TL;DR: Fix this in at-risk routing agent workflow by acting on the exact message first: record each completed assignment with account and CSM, check that record before assigning, and stop after a repeated identical assignment is detected, reporting the account whose routing state never changes as the blocker. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one account, batch or record set first, then rerun the full scope and reconcile the counts.

Not specified by the original author.

TL;DR

Fix this in the agent workflow by acting on the exact problem first: break the loop by forcing a state change, mark the current step complete or failed explicitly instead of leaving it pending, route the work on to the next step after the task to fill counterparty details into an NDA template, and watch the run log to confirm no step repeats. Do not rerun the same attempt unchanged, because the same inputs produce the same failure. Prove the fix on one run or task attempt first, then rerun the full scope and reconcile the results.

agent stuck loop detected repeating the same step while trying to fill counterparty details into an NDA template error failure

Use this when

• The operation in the agent workflow fails with this exact problem: agent stuck loop detected repeating the same step while trying to fill counterparty details into an NDA template error failure.
• The same failure repeats on retry with unchanged inputs.
• An NDA task, counterparty step or repository filing 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 agent completes the task and you only disagree with the output wording or a legal judgement in the document. That is a legal owner decision, not this failure.

Steps

1. Reproduce the failure using one run or task attempt in the agent workflow and record the full problem text plus the record, signer or run 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: break the loop by forcing a state change, mark the current step complete or failed explicitly instead of leaving it pending, route the work on to the next step after the task to fill counterparty details into an NDA template, and watch the run log to confirm no step repeats. Verify: the single failing scope now behaves as the fix predicts, or the corrected value is visible on the record.
3. Check neighbouring records, templates or runs that share the same settings, template or schedule, 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 the agent workflow 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 executed NDA, the counterparty record or the repository entry, 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 workflow log so the next occurrence is recognised immediately. Verify: the record names the problem, the fix applied and the evidence of success.

Variant phrasings

agent stuck loop detected repeating the same step while trying to fill counterparty details into an NDA template error failure

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

How to fix - agent stuck loop detected repeating the same step while trying to fill counterparty details into an NDA template error failure

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

Agent workflow 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

The agent repeats a step when the step result is not written back as state, so the planner sees the same unfinished task on every pass and selects it again.

Edge cases

• The record, template or assignment changed after the failing run started. Refresh the current state and reapply the fix against the current values, not the values from the failed run.
• The single scope proof passes but the full rerun still fails on other items. Treat each remaining failure as its own scope, because a shared template, setting or schedule can hide more than one cause.
• The source systems disagree on the correct value. The executed NDA governs wording, the counterparty record governs party details, and the workflow record governs status; record which source won and why.

Compatibility: current agent runtimes and the NDA, signature and repository tools 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/pstc4oi2JR6wpoOhtgXXi9Pg

Resolved from the public thread: https://vectle.com/posts/pstc4oi2JR6wpoOhtgXXi9Pg

Thread query: agent stuck loop detected repeating the same step while trying to fill counterparty details into an NDA template error failure

TL;DR: Fix this in the agent workflow by acting on the exact problem first: break the loop by forcing a state change, mark the current step complete or failed explicitly instead of leaving it pending, route the work on to the next step after the task to fill counterparty details into an NDA template, and watch the run log to confirm no step repeats. Do not rerun the same attempt unchanged, because the same inputs produce the same failure. Prove the fix on one run or task attempt first, then rerun the full scope and reconcile the results.