You asked
How do I setup the game?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: 7 Wonders (2nd Edition)bg-316377-en-2e · 7 Wonders (Second Edition): Armadabg-316382-en-1e
Answered before
This question didn't get an answer just now — but 7 Wonders (2nd Edition) has been asked something like it before. The corpus may have changed since, so check the date and the answerer on each one before you rule from it.
I looked through 7 Wonders (2nd Edition)'s rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.
The closest rulebook passages are below — check them before ruling.
Separate the Age cards into three decks: Age I, Age II, and Age III. Each player randomly takes a Wonder Board picking their preferred side ( Day or Night). 2 For each Age, sort the cards by the minimum number of players required and keep only the cards with a number less than or equal to the number
Take stock of the cards in your hand without showing them to the other players. From these cards, choose 1 and place it face down in front of you. Set the remaining cards aside face down. They will be used later.
Note: underlined steps refer to the 7 Wonders base game. Sort the cards from the base game by Age according to the number of players. Put the remaining cards back in the box; they won't be used for this game. Sort the Armada cards by Age and shuffle each deck thus formed. For each Age, randomly
To construct a stage of your Wonder, pay only the cost shown on your Wonder board for this stage (see Construct in 7 Wonders pages 6-7). Put your card face down under your board so that half is covered by the stage of the Wonder you are constructing. The effect of this stage is now available to you
Turn resolution always takes place in this order: Pay all construction costs (card, Wonder, and possibly Naval Construction). Move the Ship corresponding to your Naval Construction, if any. Apply all effects , with the exception of Coin losses. Resolve Island Exploration . Resolve the const
Strategy guides → — community tips, kept separate from rulings
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- warm abstain
-
- this ruling — W1 — generic warm abstain · receipt: none (generic)
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 77 ms · ask 2822 ms · total 2904 ms
- single-flight (PR-5)
- queued 0 ms · generation 2904 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.046635, "snippet": "Separate the Age cards into three decks: Age I, Age II, and Age III. Each player randomly takes a Wonder Board picking their preferred side ( Day or Night). 2 For each Age, sort the cards by the minimum number of players required and keep only the cards with a number less than or equal to the number", "headingPath": "SETUP", "sharpsignalDocId": 67}, {"page": 4, "score": 0.032522, "snippet": "Take stock of the cards in your hand without showing them to the other players. From these cards, choose 1 and place it face down in front of you. Set the remaining cards aside face down. They will be used later.", "headingPath": "1. CHOOSE A CARD", "sharpsignalDocId": 67}, {"page": 5, "score": 0.032522, "snippet": "Note: underlined steps refer to the 7 Wonders base game. \u0007 Sort the cards from the base game by Age according to the number of players. Put the remaining cards back in the box; they won't be used for this game. \u0007 Sort the Armada cards by Age and shuffle each deck thus formed. For each Age, randomly ", "headingPath": "Setup", "sharpsignalDocId": 888}, {"page": 4, "score": 0.032002, "snippet": "To construct a stage of your Wonder, pay only the cost shown on your Wonder board for this stage (see Construct in 7 Wonders pages 6-7). Put your card face down under your board so that half is covered by the stage of the Wonder you are constructing. The effect of this stage is now available to you ", "headingPath": "B. Construct a stage of your Wonder", "sharpsignalDocId": 67}, {"page": 16, "score": 0.031545, "snippet": "Turn resolution always takes place in this order: \u0007 Pay all construction costs (card, Wonder, and possibly Naval Construction). \u0007 Move the Ship corresponding to your Naval Construction, if any. \u0007 Apply all effects , with the exception of Coin losses. \u0007Resolve Island Exploration . \u0007 Resolve the const", "headingPath": "Turn Resolution · Rules for 8 Players · Setup · Game Overview", "sharpsignalDocId": 888}, {"page": 4, "score": 0.031498, "snippet": "When everyone has chosen a card, play them simultaneously . You can use this card to complete one single action from the ones listed below: Construct the Building on your card Construct a stage of your Wonder Sell the card Note: At the start of your first game, we recommend paying attention to every", "headingPath": "2. PLAY THIS CARD", "sharpsignalDocId": 67}, {"page": 4, "score": 0.03031, "snippet": "To construct the Building on your card, pay any listed costs and place it face up above your Wonder board (see Constructing in 7 Wonders pages 6-7). Once built, the Building will remain in your City until the end of the game. Important: You can never construct two identical Buildings, meaning no two", "headingPath": "A. Construct the Building on your card", "sharpsignalDocId": 67}, {"page": 7, "score": 0.029857, "snippet": "If your City does not produce the resources needed to construct a card or Wonder stage, check your neighbors' Cities. If they produce the resources you need, you can buy these resources from them. For each resource bought, give 2 Coins to the owner of the resource. This player keeps their card and c", "headingPath": "Buying resources from a neighboring City", "sharpsignalDocId": 67}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- []
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 67 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 67 boosted
- answered-before recall
-
past answered rulings were found and offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- ruling 4644 — matched by the same question (normalized, punctuation folded) — measured similarity 1.0
- ruling 4265 — matched by the same question (normalized, punctuation folded) — measured similarity 1.0
- ruling 4264 — matched by the same question (normalized, punctuation folded) — measured similarity 1.0
- debug row retained until
- Nov 13, 2026 20:45
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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | SETUP | p.3 | 0.046635 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | 1. CHOOSE A CARD | p.4 | 0.032522 (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)) | 212 |
| #3 | RULEBOOK 7 Wonders (Second Edition): Armada — Rulebook (corpus doc 888) | Setup | p.5 | 0.032522 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | B. Construct a stage of your Wonder | p.4 | 0.032002 (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 7 Wonders (Second Edition): Armada — Rulebook (corpus doc 888) | Turn Resolution · Rules for 8 Players · Setup · Game Overview | p.16 | 0.031545 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | 2. PLAY THIS CARD | p.4 | 0.031498 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | A. Construct the Building on your card | p.4 | 0.03031 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | Buying resources from a neighboring City | p.7 | 0.029857 (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 67 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 — 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 7 Wonders (Second Edition): Armada — Rulebook (corpus doc 888) | Setup | p.5 | #3 | 0.032522 (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 re-ranker chose it |
| #2 | RULEBOOK 7 Wonders (Second Edition): Armada — Rulebook (corpus doc 888) | Turn Resolution · Rules for 8 Players · Setup · Game Overview | p.16 | #5 | 0.031545 (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 re-ranker chose it |
| #3 | RULEBOOK 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | 2. PLAY THIS CARD | p.4 | #6 | 0.031498 (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 |
| #4 | RULEBOOK 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | A. Construct the Building on your card | p.4 | #7 | 0.03031 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | END OF THE GAME | p.8 | #22 | 0.012346 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | B. Construct a stage of your Wonder | p.4 | #4 | 0.032002 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | 1. CHOOSE A CARD | p.4 | #2 | 0.032522 (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 7 Wonders (2nd Edition) — Rulebook (corpus doc 67) | SETUP | p.3 | #1 | 0.046635 (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 |
|---|
generation — timing and the path taken
- timing split
- retrieval 77 ms · first delta 2827 ms · total 2904 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 77 ms · ask 2822 ms · gateway work 2904 ms · total 2904 ms
- tokens in (the prompt the answerer read)
- 1772
- tokens out (what the answerer generated)
- 9
- tok/sec
- 200.0 tok/sec — 9 output tokens in 0.045 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 38s 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
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
-
I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped
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 12), 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.