The content agent (ChatGPT) authors packs from these guides, and the repo has
documented LLM over-compliance failures: snack overload, 416/499 same-mechanic
six-question blocks, exactly-6-of-each mechanic counts. The guides banned
therapy voice but never the machine-voice failure modes.
- QUESTION_CONTENT_GUIDE.md: new section 8A "Write Like a Human" — AI-tell
phrase ban, no-exclamation/no-emoji/sentence-case rules, humor craft (joke
lives in the detail not the adjective; one absurd detail max; adult-deadpan
mock-formality register; punch at the situation never the partner; snort
test at ~1-in-4), anti-uniformity guards (guide examples are categories not
vocabulary; no template blocks in any 10 consecutive; uneven distribution
is correct), texting test. Also retitled section 18 agent-neutral.
- DAILY_SINGLE_CHOICE_WEEKDAY_SYSTEM.md (v8→v9): "Daily Voice: Human and
Funny" subsection — weekday theme is the angle not a template stem;
wildcard absurdity rules; points at 8A as authority.
- QUESTION_QUALITY_CHECKLIST.md (v10→v11): machine-voice Automatic Rejects,
implausibly-even mechanic-count repetition check, and 5 new marking reasons
(ai_voice, labeled_joke, uniform_option_grammar, guide_example_parrot,
brand_caption_voice) so patch discipline can target these failures.
Additive only: no schema/importer-contract, count, or patch-policy changes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Self-review of the wildcard authoring spec caught two real issues:
1. Count contradiction: the new Wildcard section said '+12 free' while the pack's
authoritative counts (QUESTION_SCHEMA.md daily table + metadata, and the guide's
Required Counts + Final Production Gate 'count validation') still said 500/75. A
content agent running count validation would fail, or worse delete weekday
questions to hit 500. Reconciled all four locations to the weekday pack (frozen
500) + wildcard add-on -> 511 total / 86 free / 425 premium, and folded the
wildcard set into the Final Production Gate review sampling.
2. Rotation math: the picker indexes epochDay % poolSize and wildcard days fall ~10
apart, so a pool size sharing a factor with 10 (12 is even) only surfaces a
fraction of the questions per year. Pool size must be coprime with 10 -> 11, not
12. Documented as a hard constraint so it isn't 'rounded to 10' later.
Also hardened the section: net-new (not a patch), answer_config option mirror,
unique snake_case option ids, and a QUESTION_SCHEMA.md cross-reference.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The client's DailyModeResolver promotes ~10% of days (dayOfYear % 10 == 3) to a
'Wildcard' theme, but there were zero wildcard questions and the server never
assigned one — so those days showed the Wildcard banner over a normal weekday
question. This adds the server half:
- pickDailyQuestionId now detects wildcard days (new pure, tested dayOfYearUtc /
isWildcardDay helpers mirroring the client cadence) and prefers the mode_wildcard
pool. Until that content is seeded it falls back to the day's WEEKDAY mode (not
the whole pool), so it's a safe no-op pre-content. +3 unit tests (fn 80 -> 83).
- Authoring spec for the missing content added to
seed/questions/DAILY_SINGLE_CHOICE_WEEKDAY_SYSTEM.md (## Wildcard Mode): 12 free
single_choice, day-agnostic voice, REQUIRED mode_wildcard tag, id scheme, schema,
and the post-authoring rollout (asset-db data-only insert + Firestore pointer seed
+ deploy).
Content authoring handed to another agent per the guide. Takes effect after the
wildcard rows land in app.db + Firestore and assignDailyQuestion is deployed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
null