You asked
How do I take my turn?
Answered counted as answeredAsked with: Everdell: Pearlbrookbg-259996-en-1e
On your turn, you may perform one of the following actions: 1. Play one of the Adornment cards you were dealt at the beginning of the game [1]. This counts as your action on your turn [1]. Each Adornment card costs 1 pearl to play [1]. 2. Place one of your workers on a Wonder spot to build the Wonder [1]. To do so, you must pay the listed amount of resources, pearls, and discard the listed amount of cards from your hand [1]. After paying the cost, take the model of the Wonder and place it beside your city [1].
Strategy guides → — community tips, kept separate from rulings
🔧 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 1879 ms · ask 3769 ms · total 5658 ms
- single-flight (PR-5)
- queued 0 ms · generation 5658 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.032522, "snippet": ". aes Set herr a 'Onyour turn, you 'may play one of the 'Adornment cards 'you were dealt at thebeginning of the 'game. This counts, asyour action on. your turn, Each 'Adornment card costs 1 pearl to play, and does not take up space inyoureity. 'When played, the ability on the top half ofthe card act", "headingPath": "SHOAL · ADVERTISEMENT! · ADORNMENTS · WONDERS · PEARLS", "sharpsignalDocId": 221}, {"page": 4, "score": 0.016393, "snippet": "Follow the setup rules for the normal game with these additions: Place the River board to the side of main board. Place the pearl tokens on the Shoal spat on the board. Place the Wonder boards beneath the Ever Tree, covering the costs for the basic Events (the basic Events will not be used with this", "headingPath": "SETUP", "sharpsignalDocId": 221}, {"page": 7, "score": 0.015873, "snippet": "You succeeded in chasing away that old Rapscallion before, and Everdell enjoyed. atime of peace and tranquility. However, tales ofthe new riches and beauty found in Pearlbrook have lured him out from his dark haunts, and once again he is tyingto claim Everdell for himself. You must stop him! 'When p", "headingPath": "Rugwort returns! · SETUP · GAMEPLAY", "sharpsignalDocId": 221}, {"page": 8, "score": 0.015625, "snippet": "a INOEX Bridge: Increase the amount of canis youmay hold favour hand by Lor each peayou have, Aso every Ue you gan a peat, draw 2 eas from the deck Ferry You may place your Ambassador hereto copy any reveded River Destination even ifthe 'Deltinalion fs oceupled: and even fou dont mest the requiremen", "headingPath": "GAMEPLAY", "sharpsignalDocId": 221}, {"page": 2, "score": 0.015385, "snippet": "We ne nye how aoe eter Whe we fre made cur any eo asa Eve Pe, we save de, eerste {hi regen Ate weds The es te eth wee ie end oon may, a hagh Tiel fas my pews woul me Tule dat Be ©, wefamal pry to dear pat ant der 'more eval ot adeno fe. 'Theda imo our rng heme can. or dye felons angi shes, ste ca to", "headingPath": "Zeapyoo®", "sharpsignalDocId": 221}, {"page": 1, "score": 0.015152, "snippet": "*RULES OF PLAY e+", "headingPath": "Zeapyoo®", "sharpsignalDocId": 221}, {"page": 5, "score": 0.014925, "snippet": "Your amphibious Ambassador can visit underwater locations and citizens in Pearlbrook to establish diplomatic ee connections with the waterfolk below. ana ease aa a Doing sowillgive you valuable bonuses, River Gtizenswi 'most important of which are the precious Tequire you to discard certain cards fr", "headingPath": "THE RIVER · SHOAL", "sharpsignalDocId": 221}, {"page": 2, "score": 0.014706, "snippet": "Deep below the shimmering surface of the Pearlbrook River, a mysterious civilization, of waterfolk is waiting, You will be sending your amphibious Ambassador on diplomatic journeys to trade information. and resources with the river dwellers. In exchange, you will be gathering a new and. valuable res", "headingPath": "OVERVIEW", "sharpsignalDocId": 221}]
- citations (raw)
- [{"page": 6, "quote": null, "headingPath": "SHOAL · ADVERTISEMENT! · ADORNMENTS · WONDERS · PEARLS", "sharpsignalDocId": 221}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; no base-rulebook boost — this ask EXCLUDED the base book, so its rulebook was never resolved and no id for it went on the wire (boosting it would have put that book back into a scope the reader took it out of); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
no base-rulebook boost — this ask EXCLUDED the base book, so its rulebook was never resolved and no id for it went on the wire (boosting it would have put that book back into a scope the reader took it out of)
- 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 3, 2026 20:29
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 TWO-ARM fuse (full-text + vector), whose arithmetic ceiling is 0.03279 — both arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). Measured healthy band on this fuse: 0.016–0.033. 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 Everdell: Pearlbrook — Rulebook (corpus doc 221) | SHOAL · ADVERTISEMENT! · ADORNMENTS · WONDERS · PEARLS | p.6 | 0.032522 (inside the measured healthy band 0.016–0.033) | 300 |
| #2 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | SETUP | p.4 | 0.016393 (inside the measured healthy band 0.016–0.033) | 300 |
| #3 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | Rugwort returns! · SETUP · GAMEPLAY | p.7 | 0.015873 (below the measured healthy band (< 0.016) — a weak fuse) | 300 |
| #4 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | GAMEPLAY | p.8 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse) | 300 |
| #5 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | Zeapyoo® | p.2 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse) | 300 |
| #6 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | Zeapyoo® | p.1 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse) | 17 |
| #7 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | THE RIVER · SHOAL | p.5 | 0.014925 (below the measured healthy band (< 0.016) — a weak fuse) | 300 |
| #8 | RULEBOOK Everdell: Pearlbrook — Rulebook (corpus doc 221) | OVERVIEW | p.2 | 0.014706 (below the measured healthy band (< 0.016) — a weak fuse) | 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 Everdell: Pearlbrook — Rulebook (corpus doc 221) | SHOAL · ADVERTISEMENT! · ADORNMENTS · WONDERS · PEARLS | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 1879 ms · first delta 4728 ms · total 5658 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 1879 ms · ask 3769 ms · gateway work 5658 ms · total 5658 ms
- tokens in (the prompt the answerer read)
- 3101
- tokens out (what the answerer generated)
- 129
- tok/sec
- 149.0 tok/sec — 129 output tokens in 0.866 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 29s 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 10), 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.