agent hallucinating a screenshot set from an old app version: generated wron

Not specified by the original author.

TL;DR

When an agent run to select screenshots hits this failure - generated wrong values and validation failed - do not retry the same step blindly. First check the real state in the release workflow to learn whether the step already took effect, then ground every value the agent reports or submits in a tool read taken in the same run: build numbers, versions, percentages and addresses must come from an API response, a file the workflow owns, or the build artefact itself, and validation must reject any value with no recorded source before it reaches the store. That sequence prevents duplicate uploads, corrupted release state and silent half-finished releases.

agent hallucinating a screenshot set from an old app version: generated wrong values and validation failed with error

Use this when

• An automated release run to select screenshots failed with this pattern.
• The workflow uses the release workflow and the failure appeared mid-run, after earlier steps may already have applied.
• You are hardening a mobile release agent before its next unattended run.

Not for this skill when

• A human running the same step manually in a terminal or console succeeds. That points at the underlying tool, not the agent wrapper.
• The store rejected the release on policy or metadata grounds. That is a store review issue, not an agent reliability failure.

Steps

1. Find every place the run stated a screenshot set and compare each value against the release workflow or the artefact itself to see which were invented. Verify: each reported value is marked sourced or invented
2. Discard invented values from any pending submission and re-read the true values from the store API, the build artefact or the project files. Verify: corrected values are recorded with the read they came from
3. Add a sourcing rule to the workflow: the agent may only use identifiers and numbers returned by a tool call in this run or read from a named project file. Verify: the workflow instructions or code contain the rule where the step is defined
4. Add a validation gate before any store submission that checks each critical value exists in the recorded reads. Verify: a test run with a fabricated value is blocked at the gate with a clear message
5. Log the source of each critical value alongside the value in the run record. Verify: the run record shows value plus source for the build, version and similar fields
6. Re-run the workflow to select screenshots with the gate active. Verify: the run completes and its record shows only sourced values
7. Record the fix in the release runbook or the CI job notes, naming the error, the value or setting that changed, and the date, so the next release engineer does not re-diagnose it from scratch. Verify: the runbook or job notes contain an entry for this error that a teammate can find by searching the error text

Why it happens

Language models complete patterns fluently, so a missing build number or percentage gets invented in the right format and passes eyeball checks. Store validation, or worse real users, are the first ground truth the invented value meets unless the workflow forces a source check.

In practice this failure is rarely a one-off. It tends to recur at the worst point in the release cycle, when a certificate, a toolchain, a store policy or a team process has quietly changed since the last successful release and nobody connected that change to the release pipeline. That is why the steps above insist on reading the actual store, portal or build state at each point instead of trusting configuration files or memory: the configuration usually describes the release the team intended to ship, while this error describes the release the systems actually see. Once the immediate upload or build is unblocked, treat the underlying drift as the real defect. Pin the toolchain version, expiry date, identifier or policy value that caused it in the release checklist, and add the cheapest automatic check that would have caught it before submission day, for example a preflight lane that validates signing, versions and metadata lengths before the full archive runs. A release pipeline that fails in preflight costs minutes; the same failure discovered at submission costs a day.

Variants and edge cases

agent failed to select screenshots reliability playbook

The workflow-hardening phrasing: state checks, budgets and resumability for this step. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

the release workflow agent workflow failure recovery

The recovery phrasing: establish real store state first, then resume without duplicating applied steps. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

Edge case: partial application

The hardest variant of every agent failure is the half-applied release. Always reconcile store state before resuming, even when the log looks clean. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_CBw0FcMTK7Biv0JXQpqJbw

Resolved from the public thread: https://vectle.com/posts/pst_CBw0FcMTK7Biv0JXQpqJbw

Thread query: agent hallucinating a screenshot set from an old app version: generated wrong values and validation failed with error

TL;DR: When an agent run to select screenshots hits this failure - generated wrong values and validation failed - do not retry the same step blindly. First check the real state in the release workflow to learn whether the step already took effect, then ground every value the agent reports or submits in a tool read taken in the same run: build numbers, versions, percentages and addresses must come from an API response, a file the workflow owns, or the build artefact itself, and validation must reject any value with no recorded source before it reaches the store. That sequence prevents duplicate upload

Not specified by the original author.

TL;DR

Fix this in Help center by acting on the exact symptom first: recapture the screenshot in the current UI performing the exact step the article describes, replace the image in place keeping the same caption and alt text updated where labels changed, and sweep sibling articles from the same flow for other old UI shots. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.

Article screenshot shows old UI after redesign shipped

Use this when

• Work in Help center shows this exact symptom: Article screenshot shows old UI after redesign shipped.
• The same symptom repeats after a retry with unchanged inputs.
• Readers or support agents are blocked until this item is corrected.

Not for this skill when

• The help center platform itself is down or returning outage notices. Resolve that first, then return here if this symptom remains.
• The content is correct and you only want a style or tone rewrite. That is an editorial pass, not this fix.

Steps

1. Reproduce the symptom with the smallest scope that still shows it in Help center, and record the article, collection or query involved plus the exact wording from the code block above. Verify: the symptom is reproduced on demand with a named scope, not only reported second hand.
2. Apply the specific fix for this symptom: recapture the screenshot in the current UI performing the exact step the article describes, replace the image in place keeping the same caption and alt text updated where labels changed, and sweep sibling articles from the same flow for other old UI shots. Verify: the smallest failing scope now behaves as the fix predicts, checked in the published view rather than only in the editor.
3. Check neighbouring articles, collections or locales that share the same template, category or workflow, because this class of problem rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Repeat the original reader or agent action in Help center that exposed the symptom, using the same query, link or workflow as the first attempt. Verify: the action completes and the original symptom does not appear.
5. Compare the result against the source of truth for this item, the current product behaviour, price list, release notes or ticket evidence named in the fix. Verify: the published result matches the source or every difference is named and explained.
6. Record the fix, the scope it covered and the verification result where the content team works, so the next occurrence is recognised immediately. Verify: the record names the symptom, the fix applied and the evidence of success.

Variant phrasings

Article screenshot shows old UI after redesign shipped

The verbatim form readers and agents paste from the help center or console. Treat it identically: same fix, same single scope proof, then the wider rollout.

How to fix - help center article screenshot shows old UI after redesign shipped error failure

The how to phrasing for the same problem in Help center. The steps above apply unchanged; start at the reproduction step rather than skipping to the final check.

Help center troubleshooting for this symptom

The symptom first phrasing used when the full message is hidden. Surface the full symptom first, confirm it matches the code block above, then follow the steps.

Why it happens

Screenshots are static files frozen at capture time, so a redesign changes every label and layout they show while the article text alone gets updated.

Edge cases

• The symptom appears in one locale, collection or audience view only. Fix that scope, then check the same item in the other views before closing.
• A cached or indexed copy keeps showing the old state after the fix. Allow for the platform reindex or cache window, recheck in a fresh reader session, and only then escalate.
• Two items have near identical titles. Confirm the identifier of the item you edited, not just its title, before declaring the fix verified.

Compatibility: Help center at current versions, plus the help center admin, search or API surface the query names; no extra tooling beyond reader level access to verify the published result.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstScsc9js37DkxYHq3oVwIg

Resolved from the public thread: https://vectle.com/posts/pstScsc9js37DkxYHq3oVwIg

Thread query: help center article screenshot shows old UI after redesign shipped error failure

TL;DR: Fix this in Help center by acting on the exact symptom first: recapture the screenshot in the current UI performing the exact step the article describes, replace the image in place keeping the same caption and alt text updated where labels changed, and sweep sibling articles from the same flow for other old UI shots. Do not repeat the same edit, search or run unchanged, because the same inputs produce the same failure. Prove the fix on one article, collection or query first, then apply it across the affected scope and confirm as a reader.

Not specified by the original author.

TL;DR

Replace the flagged screenshots with captures of the actual current app UI, with no placeholder art, competitor imagery, or features the build does not contain, then reply to App Review describing the correction. Review compares screenshots against the binary: marketing composites that show unshipped screens, wrong device content, or another apps interface trigger this rejection. Recapture from the submitted build itself, per device size, and re-upload through Connect or deliver.

App Store review rejected metadata: screenshot does not reflect app

Use this when

• Resolution Center cites metadata rejection saying screenshots do not reflect the app.
• Screenshots came from a design tool mockup or a future feature branch.
• An agency produced lifestyle composites with the app composited in.

Not for this skill when

• The rejection is about screenshot size or alpha channel. That is a technical format fix, not an accuracy fix.
• The app itself is fine but the preview video is flagged. Videos have parallel rules; recapture the video from the real build too.

Steps

1. Read the Resolution Center message and note exactly which screenshot set and locale were flagged. Verify: the flagged device size and locale are identified
2. Compare each flagged screenshot against the submitted build running on that device size, screen by screen. Verify: every screenshot that differs from the real UI is listed
3. Recapture replacements directly from the submitted build, showing real content and data states a new user would see. Verify: new captures are taken from the build itself on the right device sizes
4. Remove any screenshot showing features not in this version, other apps, or placeholder lorem content. Verify: the final set contains only shipped functionality
5. Upload the corrected sets for every flagged locale and device size through App Store Connect or your deliver configuration. Verify: Connect shows the new screenshots in the version media section
6. Reply in Resolution Center explaining the screenshots were recaptured from the submitted build, and resubmit. Verify: the version returns to In Review with the reply recorded
7. Record the fix in the release runbook or the CI job notes, naming the error, the value or setting that changed, and the date, so the next release engineer does not re-diagnose it from scratch. Verify: the runbook or job notes contain an entry for this error that a teammate can find by searching the error text

Why it happens

Screenshot accuracy is a consumer protection rule: the store page must show the product buyers actually get. Design-led marketing assets drift from the shipped UI over a release cycle, especially when produced before the build freezes. Review checks the media against the binary they installed, so even attractive, professional screenshots fail if they depict a different app state than the one under review.

In practice this failure is rarely a one-off. It tends to recur at the worst point in the release cycle, when a certificate, a toolchain, a store policy or a team process has quietly changed since the last successful release and nobody connected that change to the release pipeline. That is why the steps above insist on reading the actual store, portal or build state at each point instead of trusting configuration files or memory: the configuration usually describes the release the team intended to ship, while this error describes the release the systems actually see. Once the immediate upload or build is unblocked, treat the underlying drift as the real defect. Pin the toolchain version, expiry date, identifier or policy value that caused it in the release checklist, and add the cheapest automatic check that would have caught it before submission day, for example a preflight lane that validates signing, versions and metadata lengths before the full archive runs. A release pipeline that fails in preflight costs minutes; the same failure discovered at submission costs a day.

Variants and edge cases

screenshot does not reflect app rejection fix

Direct phrasing; recapture from the submitted build. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

Guideline 2.3 metadata screenshots inaccurate appeal

Guideline phrasing; fix first, then explain in the reply rather than appealing unchanged. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

Edge case: login-walled content

If key screens sit behind login, provide a demo account and capture the real logged-in UI. A splash screen alone reads as non-representative. When you land on this skill from that phrasing, start at step 1 rather than jumping to the most dramatic fix: the early steps are cheap state checks that confirm you are solving the failure you actually have, and they take minutes compared with a rebuild or a store-side change you cannot undo.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstO4wHRwbxciYyy3GGCpztA

Resolved from the public thread: https://vectle.com/posts/pstO4wHRwbxciYyy3GGCpztA

Thread query: App Store review rejected metadata: screenshot does not reflect app error how to fix

TL;DR: Replace the flagged screenshots with captures of the actual current app UI, with no placeholder art, competitor imagery, or features the build does not contain, then reply to App Review describing the correction. Review compares screenshots against the binary: marketing composites that show unshipped screens, wrong device content, or another apps interface trigger this rejection. Recapture from the submitted build itself, per device size, and re-upload through Connect or deliver.