You asked
How do I setup the game?
Answered counted as answered1. The last person to cook something goes first [1]. 2. The start player shuffles the Fortune Teller cards and puts them face down into a draw pile in front of them [1]. 3. Put the Scoring Track in the middle of the table [1]. 4. Place the Flame (turn marker) on the 1-space of the Turn Indicator [1]. 5. Place the 4 seal tiles on the 4 seal spaces with the '0' facing up [1]. 6. Lay out the orange and black books [1]. 7. Lay out only the green, blue, and red books from one set (putting the yellow and purple books off to the side) [1]. 8. Separate the ingredient chips by color and put them next to their corresponding ingredient books [1]. 9. Each player receives one pot (player board), one bag, and a scoring marker in a color of their choice, which they place on the seal tile of that same color [2]. 10. Each player places their pot in front of them with the side without the test tubes facing up [2]. 11. Each player places their droplet on the '0' space in the middle of the pot [2]. 12. Each player places a flask in their color on the large trivet next to the pot (bottom right) with the full side facing up [2]. 13. Place the rat stone on the small trivet to the left of the flask [2]. 14. Each player takes 4 white 1-chips, 2 white 2-chips, 1 white 3-chip, 1 orange 1-chip, and 1 green 1-chip and puts them into their bag [2]. 15. Each player takes 1 ruby and puts it onto the bag (left) on their player board [2].
🔧 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 210 ms · ask 6314 ms · total 6536 ms
- single-flight (PR-5)
- queued 0 ms · generation 6536 ms
- retrieval refs (raw)
- [{"page": 2, "score": 0.032522, "snippet": "The last person to cook something goes first. The start player then shuffles the Fortune Teller cards and puts them face down into a draw pile in front of them. Now put the Scoring Track in the middle of the table. The Flame goes on the 1-space of the Turn Indicator. The 4 seal tiles go on the 4 sea", "headingPath": "Setup", "sharpsignalDocId": 189}, {"page": 3, "score": 0.031778, "snippet": "Each player receives one pot (player board), one bag, and the scoring marker in the color of their choice, which they place on the seal tile of the same color. Each player places their pot in front of them with the side without the test tubes facing up, and places their droplet on the '0' space in t", "headingPath": "Setup · How to Play", "sharpsignalDocId": 189}, {"page": 8, "score": 0.031746, "snippet": "During the Potion Phase of the last turn, the start player gives the command 'Stir!', and everyone reaches into their bags and simultaneously takes out a chip. If a player wishes to stop putting ingredients into their pot, they pull their hand out of their bag with no chip. This simultaneous action ", "headingPath": "Turn Indicator · Game Variation", "sharpsignalDocId": 189}, {"page": 1, "score": 0.030415, "snippet": "Further explanation of the ingredient books You do not have to read through all the ingredient books. You only need to read the sets that are in the game, and only when new books are put onto the table. Pumpkin: Cost: An orange 1-chip costs 3 coins. Bonus: None. A 1-chip in the pot has no particular", "headingPath": "", "sharpsignalDocId": 189}, {"page": 1, "score": 0.02971, "snippet": "If a blue 4-chip is placed after a blue 2-chip, the bonus only applies for the next 4 drawn chips, not 5. If a blue 2-chip is the third placed chip after a blue 4-chip, the bonus only applies for the next 2 drawn chips. SET 3 Cost: A Blue 1-chip costs 4 coins, a 2-chip costs 8, and a 4-chip costs 14", "headingPath": "", "sharpsignalDocId": 189}, {"page": 4, "score": 0.015625, "snippet": "To prepare their potions, everyone draws chip after chip from their bags, placing them on the appropriate numbered space in their pots. There are no individual turns during the Potions Phase. Everyone prepares their potions at the same time . Even though they players are filling their pots at the sa", "headingPath": "Potions Phase", "sharpsignalDocId": 189}, {"page": 3, "score": 0.015385, "snippet": "At the beginning of each turn, the player who has the Fortune Teller cards in front of them reads the first card aloud, then lays it face up next to the Scoring Track, which starts the discard pile. The action that was read out applies for all players. If the action states that the players can take ", "headingPath": "Fortune Teller Cards", "sharpsignalDocId": 189}, {"page": 6, "score": 0.015152, "snippet": "First, everyone whose potion did not explode checks to see who has reached the highest scoring space. Some spaces have the same scoring value, in which case the furthest one from space-0 is the higher scoring space. This player gets to roll the Bonus Die for a bonus. If there is a tie, they all get ", "headingPath": "A) Bonus Die · B) Chip Actions · D) Victory Points · E) Buy Chips", "sharpsignalDocId": 189}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 189}, {"page": 3, "quote": null, "headingPath": "Setup · How to Play", "sharpsignalDocId": 189}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- 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 1, 2026 04:06
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Setup | p.2 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Setup · How to Play | p.3 | 0.031778 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Turn Indicator · Game Variation | p.8 | 0.031746 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | p.1 | 0.030415 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 | |
| #5 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | p.1 | 0.02971 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 | |
| #6 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Potions Phase | p.4 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #7 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Fortune Teller Cards | p.3 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | A) Bonus Die · B) Chip Actions · D) Victory Points · E) Buy Chips | p.6 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 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 The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Setup | p.2 | no quote on the wire |
| [2] | RULEBOOK The Quacks of Quedlinburg — Rulebook (corpus doc 189) | Setup · How to Play | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 210 ms · first delta 3600 ms · total 6536 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 210 ms · ask 6314 ms · gateway work 6536 ms · total 6536 ms
- tokens in (the prompt the answerer read)
- 3443
- tokens out (what the answerer generated)
- 399
- tok/sec
- 138.8 tok/sec — 399 output tokens in 2.874 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 32s 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
- SERVED — setup-shaped and this game's approved setup checklist is offered above
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 107), 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.