Ruling — San Juan (Second Edition)

You asked

How do I set up the game?

Answered counted as answered

1. Choose a starting player and give them the governor card [1]. 2. Lay out the 5 role cards next to each other in the center of the table [1]. 3. Shuffle the 5 trading house tiles and place them face down in a stack next to the role cards [1]. 4. Remove one indigo plant from the deck for each player [1]. 5. Shuffle the remaining cards and place them face down next to the role cards to form a supply pile [1]. 6. Give each player one indigo plant, placed face up in front of them on the table [1]. 7. Give each player four cards drawn from the top of the deck to be kept in hand and hidden from other players [1]. 8. (If using the expansion) Shuffle the 33 new cards with the cards from the basic game and place the cathedral face up next to the role cards [2].

[1] RULEBOOK San Juan (Second Edition) — Rulebook · p.2 · Game setuP (basic Game) · Game Play

[2] RULEBOOK San Juan (Second Edition) — Rulebook · p.14 · expansion: 'the new buildings' · Guard Room beginning of a round · Office building beginning of a round · hut trader phase · tavern builder phase · Park builder phase

🔧 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 214 ms · ask 5292 ms · total 5518 ms
single-flight (PR-5): queued 0 ms · generation 5518 ms
retrieval refs (raw): [{"page": 2, "score": 0.032522, "snippet": "Choose a starting player , and give this player the governor card. Lay out the 5 role cards next to each other in the center of the table. Shuffle the 5 trading house tiles and place them face down in a stack next to the role cards. Remove one indigo plant from the deck for each player. Shuffle the ", "headingPath": "Game setuP (basic Game) · Game Play", "sharpsignalDocId": 132}, {"page": 13, "score": 0.031545, "snippet": "- Devin owns a statue, a hero and a triumphal arch, and receives 6 additional victory points at the end of the game. If he also owned a city hall, he would earn an additional 4 victory points for these 4 buildings. At the end of the game, the owner of a palace receives one additional victory point f", "headingPath": "Example: · Palace game end · setuP VaRiatiOn · VarIaTIonS", "sharpsignalDocId": 132}, {"page": 14, "score": 0.031258, "snippet": "Contents : 33 cards (10 city buildings and 4 production buildings) + 1 cathedral card Setup : Shuffle the 33 new cards (with a violet border) with the cards from the basic game. Place the cathedral face up next to the role cards. Follow the rules for the basic game. At the beginning of the round, th", "headingPath": "expansion: 'the new buildings' · Guard Room beginning of a round · Office building beginning of a round · hut trader phase · tavern builder phase · Park builder phase", "sharpsignalDocId": 132}, {"page": 15, "score": 0.03055, "snippet": "At the beginning of the councillor phase, each player that owns a customs office draws 1 card from the supply and places it on the customs office (face down, without looking at it), as a good. When a player chooses to sell this good in a trader phase, the player draws 2 cards from the supply for thi", "headingPath": "customs Office councillor phase · bank beginning of the round · harbor trader phase · Goldsmith prospector phase · Residence game end", "sharpsignalDocId": 132}, {"page": 16, "score": 0.029958, "snippet": "Marie owns the following 11 buildings at the end of the game: 2 indigo plants (1), a sugar mill (2), a black market (2), a well (2), 2 tobacco storages (3), an aqueduct (3), a palace (6), a guild hall (6), and a residence (6). She scores 4+3=7 additional victory points (for the 3 different 2-cost bu", "headingPath": "Example: · cathedral builder phase · Ravensburger USa, Inc.", "sharpsignalDocId": 132}, {"page": 3, "score": 0.016129, "snippet": "Note: In a 2-player game, after each player has selected a role, the governor selects a second role (and players perform the associated action), before ending the round. Thus, in each round, 3 of the 5 roles are selected, in the order of governor - second player - governor. Each role has an associat", "headingPath": "Game Play · the Roles: · Builder ( Builder Phase: everyone builds a building ) · Roles: · Builder Role", "sharpsignalDocId": 132}, {"page": 1, "score": 0.015625, "snippet": "Andreas Seyfarth Prospector or trader? Builder or producer? Which roles will you play in the new world? Your goal is to become San Juan's most prosperous citizen. The player with the most victory points is the winner! The game is played over several rounds. Each round, players take turns selecting o", "headingPath": "Object Of the Game · Game cOntents", "sharpsignalDocId": 132}, {"page": 7, "score": 0.015385, "snippet": "The game ends immediately at the end of the builder phase in which one player has built a 12th building. Do not continue the round to the end. Players total their victory points, using the score pad: The sum of the victory points of all their buildings (using the number on the bottom of the cards) O", "headingPath": "Game enD · the buildings · 5 Production Buildings", "sharpsignalDocId": 132}]
citations (raw): [{"page": 2, "quote": null, "headingPath": "Game setuP (basic Game) · Game Play", "sharpsignalDocId": 132}, {"page": 14, "quote": null, "headingPath": "expansion: 'the new buildings' · Guard Room beginning of a round · Office building beginning of a round · hut trader phase · tavern builder phase · Park builder phase", "sharpsignalDocId": 132}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
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: Oct 31, 2026 14:05

retrieval — what the search arm returned

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 San Juan (Second Edition) — Rulebook (corpus doc 132)	Game setuP (basic Game) · Game Play	p.2	0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#2	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Example: · Palace game end · setuP VaRiatiOn · VarIaTIonS	p.13	0.031545 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#3	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	expansion: 'the new buildings' · Guard Room beginning of a round · Office building beginning of a round · hut trader phase · tavern builder phase · Park builder phase	p.14	0.031258 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#4	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	customs Office councillor phase · bank beginning of the round · harbor trader phase · Goldsmith prospector phase · Residence game end	p.15	0.03055 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#5	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Example: · cathedral builder phase · Ravensburger USa, Inc.	p.16	0.029958 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#6	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Game Play · the Roles: · Builder ( Builder Phase: everyone builds a building ) · Roles: · Builder Role	p.3	0.016129 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded))	300
#7	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Object Of the Game · Game cOntents	p.1	0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded)	300
#8	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Game enD · the buildings · 5 Production Buildings	p.7	0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded)	300

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	Game setuP (basic Game) · Game Play	p.2	no quote on the wire
[2]	RULEBOOK San Juan (Second Edition) — Rulebook (corpus doc 132)	expansion: 'the new buildings' · Guard Room beginning of a round · Office building beginning of a round · hut trader phase · tavern builder phase · Park builder phase	p.14	no quote on the wire

generation — timing and the path taken

timing split: retrieval 214 ms · first delta 4147 ms · total 5518 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 214 ms · ask 5292 ms · gateway work 5518 ms · total 5518 ms
tokens in (the prompt the answerer read): 3567
tokens out (what the answerer generated): 194
tok/sec: 148.1 tok/sec — 194 output tokens in 1.310 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s 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): set up

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 54), 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.