You asked
How should we prepare everything before the first turn?
Answered counted as answeredAsked with: Unconscious Mindbg-329500-en-1e
To prepare for the game, follow these steps: 1. Place your Office Room card into your Secondary Office Room [1]. 2. Draw Routine Client cards equal to the number of players plus one and place them face up within view of every player [1]. 3. Place a starting Grief Layer on top of each Client, then return any unused starting Grief Layers to the box [1]. 4. In reverse player order (counterclockwise, beginning with the player to the right of the starting player), each player must draft a Routine Client and set of Dream cards by completing these steps: * Choose a Routine Client with a starting Grief Layer and place them into your Primary Office Room [1]. * Draw a Latent Dream and place it face up into the leftmost space above your Primary Office Room [1]. * Choose a Manifest Dream from the display (or draw one from the top of the Manifest Dream deck) and layer it over the Latent Dream, leaving the icons at the bottom visible [1]. * Place a Therapy marker onto the Therapy track above your Client in the position equaling the sum of the Therapy points shown on your Client and Grief Layer cards combined [1]. * If there is a Victory Point icon in the space where you place your Therapy marker, immediately score the number of points shown [1]. * Place another Therapy marker onto the '0' position of the rightmost Therapy track [1]. 5. After all players have drafted Clients and Dreams, remove the starting Grief Layer from the remaining Client and return it to the box, then place this Client card face down at the bottom of the Routine Client deck [1]. 6. In clockwise order, beginning with the starting player, each player must choose a starting Notebook tile by taking the three starting Notebook tiles with the glyph matching their Office Room card [1].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 248 ms · ask 9790 ms · total 10046 ms
- single-flight (PR-5)
- queued 0 ms · generation 10046 ms
- retrieval refs (raw)
- [{"page": 22, "score": 0.032787, "snippet": "At the end of every turn, you may use Heart-Shaped Boxes to produce Therapy points, potentially Curing your Clients or reaching Catharsis. Then, if you have any empty Office Rooms, you must draft a new Client and set of Dreams for each empty Room. You may use Heart-Shaped Boxes to produce Therapy po", "headingPath": "END OF TURN · OPTIONAL: USE HEART-SHAPED BOXES · MANDATORY: DRAFT NEW CLIENTS", "sharpsignalDocId": 456}, {"page": 7, "score": 0.032258, "snippet": "Choose a player color and take the following components in that color: 1 player board 1 Office board 1 Professor figure 1 Inkpot 1 scoring marker You will need extra space around your player board to display cards and tiles, which you may gain throughout the game. Also take a set of the following co", "headingPath": "PLA YER SET UP", "sharpsignalDocId": 456}, {"page": 8, "score": 0.031746, "snippet": "Then, place this Client card face down at the bottom of the Routine Client deck. In clockwise order, beginning with the starting player, each player must choose a starting Notebook tile . Complete all of the following steps before proceeding to the next player. Take the three starting Notebook tiles", "headingPath": "PLA YER SET UP", "sharpsignalDocId": 456}, {"page": 15, "score": 0.03125, "snippet": "Once a row or column has Notebook tiles in all three spaces, it is considered complete. Each time you complete a row or column, immediately take the player-color Insight from the end of that row or column and place it into your dial's center reserve. This unlocks an Insight effect on your player boa", "headingPath": "COMPLETING ROWS & COLUMNS", "sharpsignalDocId": 456}, {"page": 12, "score": 0.030769, "snippet": "COFFEE Coffee is a resource that will help manage your Insights and interact with various actions and effects. When gaining or using Coffee, adjust your marker accordingly. Note: You may never have more than 6 Coffees. Disregard any you would gain in excess. Besides using Coffee to fulfill the requi", "headingPath": "END-GAME SIGNAL · ON YOUR TURN", "sharpsignalDocId": 456}, {"page": 9, "score": 0.030303, "snippet": "You may reposition your common Insights to other areas of your dial during play but never remove them (i.e., all seven of your common Insights must remain on your dial or in your center reserve for the entire game). When you utilize an Insight, you may choose a player-color or common Insight. Player", "headingPath": "Common Insights", "sharpsignalDocId": 456}, {"page": 10, "score": 0.029851, "snippet": "At any time on your turn, you may use Insights to gain Heart-Shaped Boxes. To do so, use one set of Major, Median, and Minor Insights (regardless of quality) to gain one HeartShaped Box (as indicated on your Office board). Tip: To make room for Heart-Shaped Boxes that would otherwise exceed your tra", "headingPath": "USING INSIGHTS TO GAIN HEART-SHAPED BOXES", "sharpsignalDocId": 456}, {"page": 8, "score": 0.029412, "snippet": "Place your Office Room card into your Secondary Office Room (i.e., the rightmost space below your Office board). Note: Your Office Room card blocks your Secondary Room until you remove your initial Client's starting Grief Layer (see page 21) . Draw Routine Client cards equal to the number of players", "headingPath": "PLA YER SET UP", "sharpsignalDocId": 456}]
- citations (raw)
- [{"page": 8, "quote": null, "headingPath": "PLA YER SET UP", "sharpsignalDocId": 456}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 456 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 456 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 7, 2026 05:07
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | END OF TURN · OPTIONAL: USE HEART-SHAPED BOXES · MANDATORY: DRAFT NEW CLIENTS | p.22 | 0.032787 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #2 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | PLA YER SET UP | p.7 | 0.032258 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | PLA YER SET UP | p.8 | 0.031746 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | COMPLETING ROWS & COLUMNS | p.15 | 0.03125 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | END-GAME SIGNAL · ON YOUR TURN | p.12 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | Common Insights | p.9 | 0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | USING INSIGHTS TO GAIN HEART-SHAPED BOXES | p.10 | 0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | PLA YER SET UP | p.8 | 0.029412 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Unconscious Mind — Rulebook (corpus doc 456) | PLA YER SET UP | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 248 ms · first delta 6598 ms · total 10046 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 248 ms · ask 9790 ms · gateway work 10046 ms · total 10046 ms
- tokens in (the prompt the answerer read)
- 3742
- tokens out (what the answerer generated)
- 385
- tok/sec
- 113.7 tok/sec — 385 output tokens in 3.386 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 28s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 386), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.