You asked
How do I setup the game?
Answered counted as answeredAsked with: Citadelsbg-205398-en-1e
The sage rests. The game continues.
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 267 ms · ask 2359 ms · total 2629 ms
- single-flight (PR-5)
- queued 0 ms · generation 2629 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.04918, "snippet": "The setup steps presented here are for your first game only. For the complete steps of setup for future games, see 'Complete Setup' on page 8. To set up your first game, follow these steps: Take the character reminder cards matching the eight characters from the list on the left and place them in th", "headingPath": "setup · playInG the GaMe", "sharpsignalDocId": 137}, {"page": 8, "score": 0.048131, "snippet": "After you have played the basic game, you can add more variety by playing with different characters and unique districts. A few scenarioes are provided on page 9; alternatively, players can choose which characters and unique districts to use in the game by following the customization rules below. Be", "headingPath": "custoMIzatIon rules · usInG 9 characters · coMplete setup", "sharpsignalDocId": 137}, {"page": 2, "score": 0.047875, "snippet": "For your first game, set aside the cards listed below and all 54 district cards with these icons in the bottom-left corner: All other cards will not be used for your first game. If you are already familiar with Citadels , feel free to use the scenarios on page 9 or the customization rules on page 8 ", "headingPath": "your fIrst GaMe", "sharpsignalDocId": 137}, {"page": 7, "score": 0.046875, "snippet": "In 2- or 3-player games, each player plays with two characters . The game is played normally, except that each player takes two turns each round (one turn for each character). Each player has only one stash of gold and one city, and each character's abilities apply only during its own turn. For exam", "headingPath": "playInG wIth 2-3 players · setup · seleCtion phase · Game enD · GeM shapes on cards", "sharpsignalDocId": 137}, {"page": 10, "score": 0.030769, "snippet": "This section explains each character's abilities in full detail. Remember, character abilities are optional (unless the word 'must' or 'cannot' is used here in the rules), and each ability can be used only once per turn at the time specified; if no time is specified, the ability can be used at any t", "headingPath": "character abIlItIes In detaIl", "sharpsignalDocId": 137}, {"page": 10, "score": 0.030303, "snippet": "characters or the Architect's increased building limit), and restrictions (such as the Navigator's inability to build districts). Y ou play with the cards in your hand, pay with the gold in your stash, gain resources from districts in your city, and build new districts in your city. You cannot use e", "headingPath": "character abIlItIes In detaIl", "sharpsignalDocId": 137}, {"page": 4, "score": 0.029851, "snippet": "Unlike the selection phase, players do not take turns in clockwise order during the turn phase. Instead, they take turns in ascending order of their chosen character's rank, which appears in the top-left corner of each character card. The crowned player calls each character number in ascending order", "headingPath": "turn phase · DistriCts", "sharpsignalDocId": 137}, {"page": 14, "score": 0.029412, "snippet": "If this character is sitting next to you, but has been killed by the Assassin, you gain three gold when that card is revealed at the end of the round. Note: The Queen cannot be used in games with fewer than five players. You can beautify up to two of your districts by assigning them each one gold fr", "headingPath": "character abIlItIes In detaIl", "sharpsignalDocId": 137}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "setup · playInG the GaMe", "sharpsignalDocId": 137}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 137 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 137 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)
- answer fence
- passed — letter density 0.91878 of 591 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 30, 2026 19:13 UTC
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 Citadels — Rulebook (corpus doc 137) | setup · playInG the GaMe | p.3 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Citadels — Rulebook (corpus doc 137) | custoMIzatIon rules · usInG 9 characters · coMplete setup | p.8 | 0.048131 (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 Citadels — Rulebook (corpus doc 137) | your fIrst GaMe | p.2 | 0.047875 (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 Citadels — Rulebook (corpus doc 137) | playInG wIth 2-3 players · setup · seleCtion phase · Game enD · GeM shapes on cards | p.7 | 0.046875 (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 Citadels — Rulebook (corpus doc 137) | character abIlItIes In detaIl | p.10 | 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 Citadels — Rulebook (corpus doc 137) | character abIlItIes In detaIl | p.10 | 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 Citadels — Rulebook (corpus doc 137) | turn phase · DistriCts | p.4 | 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 Citadels — Rulebook (corpus doc 137) | character abIlItIes In detaIl | p.14 | 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 Citadels — Rulebook (corpus doc 137) | setup · playInG the GaMe | p.3 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Citadels — Rulebook (corpus doc 137) | playInG wIth 2-3 players · setup · seleCtion phase · Game enD · GeM shapes on cards | p.7 | #4 | 0.046875 (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 Citadels — Rulebook (corpus doc 137) | turn phase · DistriCts | p.4 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Citadels — Rulebook (corpus doc 137) | character abIlItIes In detaIl | p.12 | #12 | 0.013889 (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 |
| #5 | RULEBOOK Citadels — Rulebook (corpus doc 137) | selectIon phase | p.3 | #17 | 0.012987 (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 Citadels — Rulebook (corpus doc 137) | character abIlItIes In detaIl | p.11 | #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 |
| #7 | RULEBOOK Citadels — Rulebook (corpus doc 137) | your fIrst GaMe | p.2 | #3 | 0.047875 (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 |
| #8 | RULEBOOK Citadels — Rulebook (corpus doc 137) | custoMIzatIon rules · usInG 9 characters · coMplete setup | p.8 | #2 | 0.048131 (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 Citadels — Rulebook (corpus doc 137) | setup · playInG the GaMe | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 267 ms · first delta 1704 ms · total 2629 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 267 ms · ask 2359 ms · gateway work 2629 ms · total 2629 ms
- tokens in (the prompt the answerer read)
- 2903
- tokens out (what the answerer generated)
- 179
- tok/sec
- 201.8 tok/sec — 179 output tokens in 0.887 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 5s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 4s ago)
- answerer node (the seat proxy's own header — this probe, not this ask)
- node1
- 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 59), 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.