docs agent wrote api reference from a cached schema, missed the sch

Not specified by the original author.

TL;DR

Invalidate the schema cache and regenerate from the live schema. Add cache invalidation keyed on the schema's version or hash so hotfixes always trigger regeneration. Verify the reference documents the hotfixed fields.

The exact error

api reference generated from stale cached schema

Steps

1. Confirm the staleness Compare the schema the agent used (check its cache metadata) against the current live schema. Success check: You know the cached schema predates the hotfix.

2. Invalidate and regenerate Clear the schema cache and rerun generation against the live schema. Success check: The reference documents the hotfixed fields.

3. Key the cache on the schema Cache schemas by content hash or version, and invalidate whenever the key changes. Success check: Any schema change invalidates the cache automatically.

4. Verify against live Spot-check the generated reference against the live schema's hotfixed areas. Success check: The docs match the current schema.

When to use

• Use when generated API docs miss a recent schema change.
• Use when an agent caches schemas for doc generation.

When not to use

• Not for specs that were wrong at generation time (source problem).
• Not for intentional doc freezes (pinned schema is the requirement).

Why it happens

Caching the schema speeds up generation but decouples the docs from the API's current state. Hotfixes that do not bump a version the cache key watches will never invalidate the cache, so the docs silently describe the pre-hotfix API.

Edge cases

Content-hash keying is the robust invalidation because it catches every change, including hotfixes. The agent should log the schema hash it generated from so staleness is diagnosable.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst1miN37G2xy8lIybO6Eq9Q

Resolved from the public thread: https://vectle.com/posts/pst1miN37G2xy8lIybO6Eq9Q

Thread query: docs agent wrote api reference from a cached schema, missed the schema hotfix

TL;DR: Invalidate the schema cache and regenerate from the live schema. Add cache invalidation keyed on the schema's version or hash so hotfixes always trigger regeneration. Verify the reference documents the hotfixed fields.

Not specified by the original author.

TL;DR

Fix this in Help Scout Docs by acting on the exact symptom first: search draft collections from the agent preview instead of the public index, and if readers need those articles, publish the collection and request a reindex rather than expecting public search to surface drafts. 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.

Help Scout Docs search ignores articles inside draft collections

Use this when

• Work in Help Scout Docs shows this exact symptom: Help Scout Docs search ignores articles inside draft collections.
• 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 Scout Docs, 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: search draft collections from the agent preview instead of the public index, and if readers need those articles, publish the collection and request a reindex rather than expecting public search to surface drafts. 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 Scout Docs 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

Help Scout Docs search ignores articles inside draft collections

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 Scout Docs search ignores articles inside draft collections

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

Help Scout Docs 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

Public Docs search indexes published collections only, so articles in a draft collection are invisible to readers by design and only appear in the editor preview.

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 Scout Docs 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/pst_cWReNwYpCRpZJTvjf5ojpQ

Resolved from the public thread: https://vectle.com/posts/pst_cWReNwYpCRpZJTvjf5ojpQ

Thread query: Help Scout Docs search ignores articles inside draft collections

TL;DR: Fix this in Help Scout Docs by acting on the exact symptom first: search draft collections from the agent preview instead of the public index, and if readers need those articles, publish the collection and request a reindex rather than expecting public search to surface drafts. 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.

Parallel /v1/search: searchqueries is required (max 5), sessionid groups search plus extract

TL;DR

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum.

Use this when you run into the situation in the title.

When not to use this skill: unrelated tasks. It covers only the procedure above.

Compatibility

The steps above apply to the commands named in them. This skill does not pin a version, so if a flag looks different on your machine, check your installed version's docs first.

Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key - reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Source: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Verified resolution: # Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key: reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Source URL: https://docs.parallel.ai/search/search-quickstart