You asked
How do I play?
Answered counted as answeredAsked with: Cafébg-284936-en-1e
So says the rulebook. So plays the table.
🔧 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 107 ms · ask 3727 ms · total 3836 ms
- single-flight (PR-5)
- queued 0 ms · generation 3836 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "4 GAME ROUND At the beginning of each round the master acts as follows: 1st: draws 3 Plan Cards from the deck and places them face up on the table; 2nd: in clockwise order instructs each player to take, or buy (see below) one Plan Card. The card is immediately replaced from the draw deck so that eac", "headingPath": "", "sharpsignalDocId": 1109}, {"page": 13, "score": 0.032258, "snippet": "13 1-4 Players 30’10 RULES GAME ROUND CHANGES At the beginning of each round the master acts as follows: 1st: draws 4 Plan Cards from the deck and places them face up on the table; 2nd: in clockwise order instructs each player to take, or buy one Plan Card. The card is immediately replaced from the ", "headingPath": "", "sharpsignalDocId": 1109}, {"page": 3, "score": 0.031746, "snippet": "Place the small wooden cubes in 4 supply piles (yellow, brown, green, red) on the table, in reach of all players. 1 Each player takes a Company Card and the associated Initial Card, which have matching backs. Each player places a white cube on the space with number 1 of the action points table. 2 Ea", "headingPath": "SETUP · Note", "sharpsignalDocId": 1109}, {"page": 6, "score": 0.03125, "snippet": "The game has four possible action types, all performed in the business area of each player. To perform any action the players spend an action point. The player takes one cube from the general supply and places it in a square with a bean icon of the matching color (A square). The square must be empty", "headingPath": "ACTIONS · PRODUCE · Example 2 · Example 3", "sharpsignalDocId": 1109}, {"page": 10, "score": 0.030769, "snippet": "10 GENERAL RULES a) The number of visible cups in the business area after placing the Plan Card indicates how many action points players can spend in this round. But, at most, players will be able to perform 8 actions, even if they have 9 cup illustrations in the business area. b) Players must alway", "headingPath": "", "sharpsignalDocId": 1109}, {"page": 14, "score": 0.030622, "snippet": "With the second edition of the CAFÉ game, PYTHAGORAS opens a small collection that, in the coming years, will bring everyone a little more of the history and culture of Portugal. Following the present game matrix, whether components aspects, or in the creative and playful design proposal, the 5 QUIN", "headingPath": "Score Scale · GAME DESIGN: Rôla & Costa · FOLLOW US:", "sharpsignalDocId": 1109}, {"page": 12, "score": 0.030303, "snippet": "12 ADVANCED VARIANT Experienced players can try this variant which adds an auction for the role of the master at the beginning of each round. The following changes are made to the rules. SETUP Remove from the deck the 8 cards with the star on the back ( ), shuffle the Plan Cards and put the deck fac", "headingPath": "", "sharpsignalDocId": 1109}, {"page": 1, "score": 0.029851, "snippet": "In 1713, King D. Joao V ordered Sergeant Melo de Palheta to travel to French Guiana and secretly bring coffee seeds to sow in Brazil. In 1800, Brazil was already one of the greatest coffee producers in the world. Drinking coffee became popular in Portuguese culture and, in the early 20th century, co", "headingPath": "GAME OBJECTIVE", "sharpsignalDocId": 1109}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 1109}, {"page": 10, "quote": null, "headingPath": "", "sharpsignalDocId": 1109}, {"page": 6, "quote": null, "headingPath": "ACTIONS · PRODUCE · Example 2 · Example 3", "sharpsignalDocId": 1109}, {"page": 7, "quote": null, "headingPath": "", "sharpsignalDocId": 1109}, {"page": 1, "quote": null, "headingPath": "GAME OBJECTIVE", "sharpsignalDocId": 1109}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1109 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1109 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 0.92115 of 1560 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 15:39 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 Café — Rulebook (corpus doc 1109) | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 | |
| #2 | RULEBOOK Café — Rulebook (corpus doc 1109) | p.13 | 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 | |
| #3 | RULEBOOK Café — Rulebook (corpus doc 1109) | SETUP · Note | 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 |
| #4 | RULEBOOK Café — Rulebook (corpus doc 1109) | ACTIONS · PRODUCE · Example 2 · Example 3 | p.6 | 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 |
| #5 | RULEBOOK Café — Rulebook (corpus doc 1109) | 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 Café — Rulebook (corpus doc 1109) | Score Scale · GAME DESIGN: Rôla & Costa · FOLLOW US: | p.14 | 0.030622 (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 Café — Rulebook (corpus doc 1109) | 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 | |
| #8 | RULEBOOK Café — Rulebook (corpus doc 1109) | GAME OBJECTIVE | p.1 | 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 |
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 18 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 Café — Rulebook (corpus doc 1109) | p.4 | #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 Café — Rulebook (corpus doc 1109) | ACTIONS · PRODUCE · Example 2 · Example 3 | p.6 | #4 | 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 |
| #3 | RULEBOOK Café — Rulebook (corpus doc 1109) | p.12 | #7 | 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 | |
| #4 | RULEBOOK Café — Rulebook (corpus doc 1109) | GAME OBJECTIVE | p.1 | #8 | 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 |
| #5 | RULEBOOK Café — Rulebook (corpus doc 1109) | p.10 | #5 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it | |
| #6 | RULEBOOK Café — Rulebook (corpus doc 1109) | p.7 | #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 | |
| #7 | RULEBOOK Café — Rulebook (corpus doc 1109) | p.13 | #2 | 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 | |
| #8 | RULEBOOK Café — Rulebook (corpus doc 1109) | SETUP · Note | p.3 | #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)) | vector + 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 Café — Rulebook (corpus doc 1109) | p.4 | no quote on the wire | |
| [2] | RULEBOOK Café — Rulebook (corpus doc 1109) | p.10 | no quote on the wire | |
| [3] | RULEBOOK Café — Rulebook (corpus doc 1109) | ACTIONS · PRODUCE · Example 2 · Example 3 | p.6 | no quote on the wire |
| [4] | RULEBOOK Café — Rulebook (corpus doc 1109) | p.7 | no quote on the wire | |
| [5] | RULEBOOK Café — Rulebook (corpus doc 1109) | GAME OBJECTIVE | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 107 ms · first delta 1480 ms · total 3836 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 107 ms · ask 3727 ms · gateway work 3836 ms · total 3836 ms
- tokens in (the prompt the answerer read)
- 3222
- tokens out (what the answerer generated)
- 459
- tok/sec
- 200.2 tok/sec — 459 output tokens in 2.293 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 31s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 3s 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
- 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 1039), 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.