Ruling — Azul: Stained Glass of Sintra

You asked

How do I setup the game?

Answered counted as answered

Asked with: Azul: Stained Glass of Sintrabg-256226-en-1e

1. Place the Factory displays (A) with the orange-framed side up in a circle around the center of the table: 5 displays for a 2-player game, 7 for a 3-player game, and 9 for a 4-player game [1]. 2. Return any unused Factory displays to the box [1]. 3. Place the glass tower (B) beside the Factory displays within reach of all players [1]. 4. Each player chooses a player color and receives the palace board (C) of that color, placing it in front of them, ensuring all players use the same side (either side A or B) [1]. 5. Each player receives 8 double-sided pattern strips of their color, shuffles them, and places one at random above each of the 8 spires of their palace board (D) [1]. 6. If a player placed the side with 2 gray joker spaces facing up, they must flip that strip over so the joker spaces face downwards [1]. 7. Each player takes the glazier (E) of their color and places it above their leftmost pattern strip [1].

[1] RULEBOOK Azul: Stained Glass of Sintra — Rulebook · p.2 · Game Setup

🔧 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 231 ms · ask 4324 ms · total 4565 ms
single-flight (PR-5): queued 0 ms · generation 4565 ms
retrieval refs (raw): [{"page": 2, "score": 0.04918, "snippet": "Place the Factory displays (A) with the orange-framed side up in a circle around the center of the table: In a 2-player game, place 5 Factory displays. In a 3-player game, place 7 Factory displays. In a 4-player game, place 9 Factory displays. Return any unused Factory displays to the box. Note: If ", "headingPath": "Game Setup", "sharpsignalDocId": 96}, {"page": 6, "score": 0.047379, "snippet": "Here is how you can set up and play the game: During step 1 of the setup: Flip the Factory displays to their back. Each of them shows 5 sectors: one for each type of pane piece, made recognizable by their color and the different shapes engraved in them. On 5 of the Factory displays, one sector is mo", "headingPath": "Diffif iculties distinguishing the colors of the pane pieces?", "sharpsignalDocId": 96}, {"page": 5, "score": 0.046642, "snippet": "If, at the end of any player's turn, there are no pane pieces left on any Factory displays AND in the center of the table, the round ends. Now, the player in charge of the scoring board must remove the top pane piece of the round indicator and drop it in the glass tower. When all spaces of the round", "headingPath": "End of the round", "sharpsignalDocId": 96}, {"page": 3, "score": 0.032258, "snippet": "The game is played over 6 rounds. Each round begins as follows: First, the player with the starting player tile places it in the center of the table. Then he takes the first turn of the round. Afterwards, play proceeds clockwise with the players taking turns until all pane pieces from the Factory di", "headingPath": "Playing the game", "sharpsignalDocId": 96}, {"page": 3, "score": 0.031746, "snippet": "In this step, you must EITHER: Pick all pane pieces of one color from any one Factory display and then move any remaining pane pieces from this Factory display to the center of the table. Move your glazier back to the leftmost pattern strip - Check if the pattern is complete OR Pick all pane pieces ", "headingPath": "Step 1- Pick pane pieces of one color", "sharpsignalDocId": 96}, {"page": 2, "score": 0.030303, "snippet": "9 Factory displays 4 palace boards (1 of each player color) 32 pattern strips (8 of each player color) 4 glaziers (1 of each player color) 8 markers (2 of each player color) 100 pane pieces (20 of each of the 5 colors) 1 scoring board 1 starting player tile 1 bag, 1 glass tower The player who most r", "headingPath": "Components", "sharpsignalDocId": 96}, {"page": 5, "score": 0.029851, "snippet": "After the sixth round, the game ends. Then the final scoring phase occurs. To determine your final score, each of you must carry out the following 3 steps: On the score track, gain 1 point for every 3 pane pieces left on your pattern strips. Lose the points shown to the right of your marker on the b", "headingPath": "End of the game", "sharpsignalDocId": 96}, {"page": 4, "score": 0.029412, "snippet": "Place each of the pane pieces you picked in step 1 onto an empty pattern space of its color on one of your strips. Bear the following rules in mind: The pieces you picked must be placed onto spaces of the same pattern strip (this means that you cannot allot them across different strips). This patter", "headingPath": "Step 2 - Place the pane pieces on one of your pattern strips", "sharpsignalDocId": 96}]
citations (raw): [{"page": 2, "quote": null, "headingPath": "Game Setup", "sharpsignalDocId": 96}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 96 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 96 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 3, 2026 05:53

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 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 Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Game Setup	p.2	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Diffif iculties distinguishing the colors of the pane pieces?	p.6	0.047379 (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 Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	End of the round	p.5	0.046642 (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 Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Playing the game	p.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))	300
#5	RULEBOOK Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Step 1- Pick pane pieces of one color	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
#6	RULEBOOK Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Components	p.2	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 Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	End of the game	p.5	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 Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Step 2 - Place the pane pieces on one of your pattern strips	p.4	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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Azul: Stained Glass of Sintra — Rulebook (corpus doc 96)	Game Setup	p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 231 ms · first delta 2720 ms · total 4565 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 231 ms · ask 4324 ms · gateway work 4565 ms · total 4565 ms
tokens in (the prompt the answerer read): 2067
tokens out (what the answerer generated): 245
tok/sec: 137.3 tok/sec — 245 output tokens in 1.785 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 20s 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 27), 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.