You asked
How do I setup the game?
Answered counted as answeredAsked with: Everdellbg-199792-en-1e
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 275 ms · ask 6579 ms · total 6867 ms
- single-flight (PR-5)
- queued 0 ms · generation 6867 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 8, "score": 0.048916, "snippet": "HOw TO PLAY cxchuve and shared (portrayed with tiny wish an exclsie locaton. Muliple workers, even of the same color, may Vat shared loeallon ke turns performing one ns. Th med in any order action may beta = Place a Worke or Play a Card Galiene sais or Prepare for: 'To visit a location, place one of", "headingPath": "SETUP · Forest LOCATIONS", "sharpsignalDocId": 113}, {"page": 16, "score": 0.047163, "snippet": "Select a player color for Rugwort (he prefers black) and set up the game According to the two-player setup. You have a starting hand ofS cards, and Rugwort does not have a hand of cards. 'Take one of Rugwort's workers and place it on the top-left Forest card, blocking it Place his other worker on th", "headingPath": "YEAR k 'RUGWORT THE RASCAL", "sharpsignalDocId": 113}, {"page": 6, "score": 0.032258, "snippet": "1) Place the board on the table. Place the Ever Tree on the stump at the top of the board. Place the twigs, resin, pebbles, and berries in piles along the bank of the river. Place the point tokens and 'occupied takens beside the board, Shuffle the Forest cards and place them on the forest clearings.", "headingPath": "SETUP", "sharpsignalDocId": 113}, {"page": 3, "score": 0.031746, "snippet": "In Everdell you willbe deploying workers to various locations on the board in order to gather resources, 'which you will use to play eards faceup infront of you, forming your own woodland city. Each turn you will perform only one of three possible actions Place a Worker Play a Card Prepare for Seaso", "headingPath": "OVERVIEW", "sharpsignalDocId": 113}, {"page": 10, "score": 0.03125, "snippet": "'You may play one card. To play a card, 'you must pay the listed requirements into the general supply. Cards may be played from either the Meadow cards or from your hand, You will be playing these cards in front of youto form your city. There are two types of cards in the game: Critters and Construc", "headingPath": "PLAY A CARD · CRITTERS", "sharpsignalDocId": 113}, {"page": 12, "score": 0.030303, "snippet": "Ifyou have placed all of your workers and you cannot play a card or do not wish to, then you must prepare for the next season. On your turn, bring back all of your deployed workers, then gain the listed bonuses for the next season, as shown atop the Ever Tree. After doing so, your turn is finished, ", "headingPath": "PREPARE FOR SEASON", "sharpsignalDocId": 113}, {"page": 19, "score": 0.029851, "snippet": "'Queen: When you place a worker here, you may Play any card from your hand or the Meadow ards worth up to 3 points for re. This refers to 'the base points of the card, not bonus points Ranger: When played, move any 1 of your deployed workers to anew location, following the normal worker placement ru", "headingPath": "CRITTERS", "sharpsignalDocId": 113}, {"page": 9, "score": 0.029412, "snippet": "You may place a worker on any Destination eard in your city, or on a Destination card in another ety that has an BEDE symbol, in which case the owner ofthe Destination gains 1 point token from the supply. Gnd Tor Bosna ane 'You may also place 1 of your workers on any remaining basic Event or special", "headingPath": "Forest LOCATIONS · EVENTS · HAVEN · JourNey", "sharpsignalDocId": 113}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "SETUP", "sharpsignalDocId": 113}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 113 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 113 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 9, 2026 23:49
retrieval — what the passage search returned
what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
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 Everdell — Rulebook (corpus doc 113) | SETUP · Forest LOCATIONS | p.8 | 0.048916 (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 Everdell — Rulebook (corpus doc 113) | YEAR k 'RUGWORT THE RASCAL | p.16 | 0.047163 (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 Everdell — Rulebook (corpus doc 113) | SETUP | p.6 | 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 |
| #4 | RULEBOOK Everdell — Rulebook (corpus doc 113) | OVERVIEW | p.3 | 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 |
| #5 | RULEBOOK Everdell — Rulebook (corpus doc 113) | PLAY A CARD · CRITTERS | p.10 | 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 |
| #6 | RULEBOOK Everdell — Rulebook (corpus doc 113) | PREPARE FOR SEASON | p.12 | 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 Everdell — Rulebook (corpus doc 113) | CRITTERS | p.19 | 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 Everdell — Rulebook (corpus doc 113) | Forest LOCATIONS · EVENTS · HAVEN · JourNey | p.9 | 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 |
what the answerer read — the passages it actually had in front of it
what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.
candidate pool: the answering read scored 26 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Everdell — Rulebook (corpus doc 113) | SETUP | p.6 | #3 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Everdell — Rulebook (corpus doc 113) | SETUP · Forest LOCATIONS | p.8 | #1 | 0.048916 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Everdell — Rulebook (corpus doc 113) | CONSTRUCTIONS, | p.21 | #13 | 0.013699 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #4 | RULEBOOK Everdell — Rulebook (corpus doc 113) | OVERVIEW | p.3 | #4 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Everdell — Rulebook (corpus doc 113) | CONSTRUCTIONS, | p.20 | #10 | 0.014286 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Everdell — Rulebook (corpus doc 113) | PLAY A CARD · CRITTERS | p.10 | #5 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Everdell — Rulebook (corpus doc 113) | PREPARE FOR SEASON | p.12 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Everdell — Rulebook (corpus doc 113) | YEAR k 'RUGWORT THE RASCAL | p.16 | #2 | 0.047163 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
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 — Rulebook (corpus doc 113) | SETUP | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 275 ms · first delta 4722 ms · total 6867 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 275 ms · ask 6579 ms · gateway work 6867 ms · total 6867 ms
- tokens in (the prompt the answerer read)
- 3056
- tokens out (what the answerer generated)
- 311
- tok/sec
- 150.0 tok/sec — 311 output tokens in 2.074 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- 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 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.