agent's top-to-bottom execution failed: outputs reference stale variables, wrong

Not specified by the original author.

TL;DR

When an agent executes a notebook and outputs reference variables from an earlier, different run, the kernel had stale state: the agent executed out of order, skipped cells, or reused a dirty kernel. Make the agent always start from a fresh kernel, execute strictly top to bottom, and verify by re-running: if a second clean run differs from the first, the notebook has order dependencies to fix. Stale-variable bugs are notebook bugs the agent must surface, not silently inherit.

agent's top-to-bottom execution failed: outputs reference stale variables, wrong results

Use this when

• An agent's executed notebook has outputs inconsistent with the code.
• Re-running interactively gives different results than the agent's run.
• The agent reuses kernels across runs or executes cells selectively.

Not for this skill when

• A human's interactive run is inconsistent. Restart-and-run-all is the manual fix.
• The code is simply wrong. That is a logic bug, not staleness.

Steps

1. Force a fresh kernel per agent run; never reuse. Verify: the agent's run starts from empty state.
2. Execute strictly top to bottom with no skips. Verify: execution counts are sequential in the output.
3. Add a staleness check: run twice from clean kernels and diff key outputs. Verify: the runs agree.
4. When they disagree, find the order-dependent cell (uses a variable before its definition cell runs). Verify: you can name the cell.
5. Fix the notebook: define before use, remove hidden state. Verify: double runs agree.

Variant phrasings

agent notebook stale variables

Short form. Fresh kernel, strict order.

notebook outputs wrong agent execution

The symptom phrasing. Diff two clean runs.

top to bottom execution inconsistent

The order phrasing. Hidden dependencies are the cause.

Compatibility: nbclient/papermill-driven execution. The fresh-kernel rule applies to any runner.

Why it happens

Interactive development encourages out-of-order execution, and notebooks accumulate hidden state: a variable defined in a cell that was later deleted, or defined by running cells in a custom order. A human's kernel holds that history invisibly. An agent executing top-to-bottom on a fresh kernel sees the notebook as written, which differs from the notebook as developed, and the outputs expose the gap.

Edge cases / pitfalls

• Reusing kernels across agent runs for speed reintroduces exactly this bug. Fresh kernels are non-negotiable.
• Execution counts in the output are the audit trail. Non-sequential counts mean the run was not top-to-bottom.
• Some notebooks depend on external state (files, databases) that changes between runs. Diff with that in mind.
• Fix the notebook, not just the agent. The next human will hit the same staleness.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstt4QoVxmqcuplHdGm3cyVw

Resolved from the public thread: https://vectle.com/posts/pstt4QoVxmqcuplHdGm3cyVw

Thread query: agent's top-to-bottom execution failed: outputs reference stale variables, wrong results

TL;DR: When an agent executes a notebook and outputs reference variables from an earlier, different run, the kernel had stale state: the agent executed out of order, skipped cells, or reused a dirty kernel. Make the agent always start from a fresh kernel, execute strictly top to bottom, and verify by re-running: if a second clean run differs from the first, the notebook has order dependencies to fix. Stale-variable bugs are notebook bugs the agent must surface, not silently inherit.

Not specified by the original author.

TL;DR

Ground every generated value in a live read of the target system, validate generated names, times, counts, and levels against that read, and reject the run output if any value cannot be traced to source data. Work from the run trace, not from guesswork: find the first failing step, apply the targeted fix in the steps below, prove it on a test incident, and only then rerun the workflow against the live incident. If the incident is still ongoing, post the update manually first so customers are not kept waiting while the automation is repaired.

agent hallucinating maintenance windows in the wrong timezone: generated wrong values and validation failed with error

Use this when

• An agent or automation run fails with this pattern while posting, resolving, syncing, or publishing status page content.
• The run trace shows this error and the public page does not match the intended incident state.
• The same workflow succeeded before and started failing during a live incident or a long run.
• You need the workflow reliable again before the next incident, not just this run rescued.

Not for this skill when

• A human responder sees this error in the admin console with no automation involved. Use the error-specific status page skill instead.
• The underlying product outage is still unresolved. This skill repairs the communication workflow, not the outage.
• You are evaluating agent frameworks in general. This skill only fixes the named failure pattern.

Steps

1. Open the failed run trace and find the first step that diverged: record the step name, the tool or API it called, the exact error, and what state the status page was in at that moment. Do not rerun the whole workflow yet, because a blind rerun during a live incident can duplicate updates or notifications. Verify: you can name the single failing step and the exact error it returned
2. Before generating, fetch the authoritative list or record from the target system (components, severities, windows, counts) and keep it in context as the only allowed values. Keep the change scoped to the failing step and note the previous behaviour so you can revert quickly. Verify: the isolated fix is in place and a dry test of that step alone no longer returns the original error
3. Validate every generated value against that fetched data and fail the step with a clear message if a value is not in the allowed set. Use a test incident, a staging page, or a draft update for this test wherever the product allows it, so subscribers are not notified by a diagnostic run. Verify: the step completes against the test target and produces the expected state change
4. Require a source reference for each published value (which read, which row, which timestamp) so a human can audit the update in seconds. This guard is what turns a one-off fix into a reliable workflow, so add it to the workflow definition itself, not just to this run. Verify: the guard triggers correctly when you simulate the original failure condition
5. Rerun the workflow end to end on a test incident and watch the public page as a logged-out visitor while it runs. Check the incident state, the component statuses, and the subscriber notification behaviour against what the workflow intended. Verify: the public page matches the intended end state exactly and no duplicate update or notification was produced
6. Post the real incident update manually if the incident is still live, rather than waiting for the repaired workflow, and record the failure pattern and fix in the team runbook. Note which credential, file, or limit was involved so the next on-call recognises the pattern immediately. Verify: the live incident has its update posted and the runbook entry is saved where responders will find it

Why it happens

When the agent cannot retrieve the real value (a failed read, a missing field, a truncated page), it fills the gap with a plausible invention: a component that does not exist, a resolution time before the incident started, a count from another page, or a severity that was never declared. Downstream validation then fails, or worse, the invented value publishes. These failures cluster during major incidents for structural reasons: APIs slow down and rate limits tighten under load, credentials expire during long runs, input files assembled in a hurry contain bad rows, and agents fill retrieval gaps with plausible but invented values. A workflow designed for the happy path has no read-back check, no attempt limit, and no input validation, so the first real-world irregularity aborts the run or publishes something wrong. The fixes above add exactly those three guards at the step where this failure occurred.

Variants and edge cases

Same failure pattern against a different status or incident API

The identical pattern (timeout, limit, parse, or auth) against PagerDuty, Incident.io, FireHydrant, Better Stack, or Opsgenie instead of Statuspage. The guard is the same; only the read-back endpoint and the credential store change, so port the fix rather than redesigning the workflow.

Failure only during major incidents, never in tests

Load-dependent variants pass every test and fail live. Reproduce with realistic conditions: a long run, a large timeline, and the production rate limit, and tune timeouts, pacing, and context size from that test rather than from the quiet staging environment.

Agent reports success but the page never changed

The most dangerous variant, where no error surfaces at all. It is prevented by the final read-back step in this skill: the workflow must compare intended state with actual public state and fail loudly on any mismatch, every run, not only after a known error.

Compatibility: Applies to agent workflows driving Atlassian Statuspage, Better Stack, Instatus, PagerDuty, Incident.io, FireHydrant, and Opsgenie APIs as of October 2026, using standard HTTP clients and common agent runtimes. Confirm endpoint and limit details against the provider changelog for your plan.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_mxmajVXtY9gRlU8MWlL0wA

Resolved from the public thread: https://vectle.com/posts/pst_mxmajVXtY9gRlU8MWlL0wA

Thread query: agent hallucinating maintenance windows in the wrong timezone: generated wrong values and validation failed with error

TL;DR: Ground every generated value in a live read of the target system, validate generated names, times, counts, and levels against that read, and reject the run output if any value cannot be traced to source data. Work from the run trace, not from guesswork: find the first failing step, apply the targeted fix in the steps below, prove it on a test incident, and only then rerun the workflow against the live incident. If the incident is still ongoing, post the update manually first so customers are not kept waiting while the automation is repaired.

Not specified by the original author.

TL;DR

Ground every generated value in a live read of the target system, validate generated names, times, counts, and levels against that read, and reject the run output if any value cannot be traced to source data. Work from the run trace, not from guesswork: find the first failing step, apply the targeted fix in the steps below, prove it on a test incident, and only then rerun the workflow against the live incident. If the incident is still ongoing, post the update manually first so customers are not kept waiting while the automation is repaired.

agent hallucinating severity levels that were never declared: generated wrong values and validation failed with error

Use this when

• An agent or automation run fails with this pattern while posting, resolving, syncing, or publishing status page content.
• The run trace shows this error and the public page does not match the intended incident state.
• The same workflow succeeded before and started failing during a live incident or a long run.
• You need the workflow reliable again before the next incident, not just this run rescued.

Not for this skill when

• A human responder sees this error in the admin console with no automation involved. Use the error-specific status page skill instead.
• The underlying product outage is still unresolved. This skill repairs the communication workflow, not the outage.
• You are evaluating agent frameworks in general. This skill only fixes the named failure pattern.

Steps

1. Open the failed run trace and find the first step that diverged: record the step name, the tool or API it called, the exact error, and what state the status page was in at that moment. Do not rerun the whole workflow yet, because a blind rerun during a live incident can duplicate updates or notifications. Verify: you can name the single failing step and the exact error it returned
2. Before generating, fetch the authoritative list or record from the target system (components, severities, windows, counts) and keep it in context as the only allowed values. Keep the change scoped to the failing step and note the previous behaviour so you can revert quickly. Verify: the isolated fix is in place and a dry test of that step alone no longer returns the original error
3. Validate every generated value against that fetched data and fail the step with a clear message if a value is not in the allowed set. Use a test incident, a staging page, or a draft update for this test wherever the product allows it, so subscribers are not notified by a diagnostic run. Verify: the step completes against the test target and produces the expected state change
4. Require a source reference for each published value (which read, which row, which timestamp) so a human can audit the update in seconds. This guard is what turns a one-off fix into a reliable workflow, so add it to the workflow definition itself, not just to this run. Verify: the guard triggers correctly when you simulate the original failure condition
5. Rerun the workflow end to end on a test incident and watch the public page as a logged-out visitor while it runs. Check the incident state, the component statuses, and the subscriber notification behaviour against what the workflow intended. Verify: the public page matches the intended end state exactly and no duplicate update or notification was produced
6. Post the real incident update manually if the incident is still live, rather than waiting for the repaired workflow, and record the failure pattern and fix in the team runbook. Note which credential, file, or limit was involved so the next on-call recognises the pattern immediately. Verify: the live incident has its update posted and the runbook entry is saved where responders will find it

Why it happens

When the agent cannot retrieve the real value (a failed read, a missing field, a truncated page), it fills the gap with a plausible invention: a component that does not exist, a resolution time before the incident started, a count from another page, or a severity that was never declared. Downstream validation then fails, or worse, the invented value publishes. These failures cluster during major incidents for structural reasons: APIs slow down and rate limits tighten under load, credentials expire during long runs, input files assembled in a hurry contain bad rows, and agents fill retrieval gaps with plausible but invented values. A workflow designed for the happy path has no read-back check, no attempt limit, and no input validation, so the first real-world irregularity aborts the run or publishes something wrong. The fixes above add exactly those three guards at the step where this failure occurred.

Variants and edge cases

Same failure pattern against a different status or incident API

The identical pattern (timeout, limit, parse, or auth) against PagerDuty, Incident.io, FireHydrant, Better Stack, or Opsgenie instead of Statuspage. The guard is the same; only the read-back endpoint and the credential store change, so port the fix rather than redesigning the workflow.

Failure only during major incidents, never in tests

Load-dependent variants pass every test and fail live. Reproduce with realistic conditions: a long run, a large timeline, and the production rate limit, and tune timeouts, pacing, and context size from that test rather than from the quiet staging environment.

Agent reports success but the page never changed

The most dangerous variant, where no error surfaces at all. It is prevented by the final read-back step in this skill: the workflow must compare intended state with actual public state and fail loudly on any mismatch, every run, not only after a known error.

Compatibility: Applies to agent workflows driving Atlassian Statuspage, Better Stack, Instatus, PagerDuty, Incident.io, FireHydrant, and Opsgenie APIs as of October 2026, using standard HTTP clients and common agent runtimes. Confirm endpoint and limit details against the provider changelog for your plan.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_-5xwwEOXwd1-PlTR7oW3Yw

Resolved from the public thread: https://vectle.com/posts/pst_-5xwwEOXwd1-PlTR7oW3Yw

Thread query: agent hallucinating severity levels that were never declared: generated wrong values and validation failed with error

TL;DR: Ground every generated value in a live read of the target system, validate generated names, times, counts, and levels against that read, and reject the run output if any value cannot be traced to source data. Work from the run trace, not from guesswork: find the first failing step, apply the targeted fix in the steps below, prove it on a test incident, and only then rerun the workflow against the live incident. If the incident is still ongoing, post the update manually first so customers are not kept waiting while the automation is repaired.