You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: San Juanbg-8217-en-1e
1. Select a starting player using any method desired [1]. 2. The starting player takes the governor placard [1]. 3. Place the 5 role placards next to each other in the middle of the table [1]. 4. Shuffle the 5 trading house tiles face down and place them in a stack face down next to the trader placard [1]. 5. Each player takes one Indigo plant card (sorted out from all the cards) and places it face up in his play area as his first building [1]. 6. Each player takes 4 face down cards from the card supply (after shuffling it) and takes them in his hand, keeping them secret from other players [1]. 7. Place the remaining cards as a face down card supply next to the role cards [1]. 8. Place the discard stack opposite the card supply [1]. 9. Place the scoring pad and pencil to the side [1].
🔧 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 225 ms · ask 5410 ms · total 5643 ms
- single-flight (PR-5)
- queued 0 ms · generation 5643 ms
- retrieval refs (raw)
- [{"page": 2, "score": 0.032787, "snippet": "The players select a starting player using any method they want. He takes the g overnor placard. Place the 5 role placards next to each other in the middle of the table. Shuffle the 5 trading house tiles face down and place them in a stack face down next to the trader placard. Each player takes one ", "headingPath": "PREPARATION", "sharpsignalDocId": 459}, {"page": 4, "score": 0.032258, "snippet": "Producer (producer phase ❖☎ all produce goods) The player, who chose this role (i.e. the producer), begins the goods production. He takes one card from the card supply and places it face down, without looking at the face up side, on any one of his empty (i.e. where no card already lies) production b", "headingPath": "Each role · Note:", "sharpsignalDocId": 459}, {"page": 6, "score": 0.031746, "snippet": "After each player has chosen a role and the players have taken the associated actions and privileges, the round ends. Players return the used role placards to the middle of the table. The governor's left neighbor takes the governor placard, becoming the new governor. The new governor reminds the own", "headingPath": "A new round · GAME END · The buildings", "sharpsignalDocId": 459}, {"page": 2, "score": 0.03125, "snippet": "The game is played over several rounds (usually between 11 and 14 rounds). Each round runs as described below. The governor (the starting player) begins. He takes one of the role placards from the middle of the table, places it face up in his play area, and takes the action associated with this role", "headingPath": "PLAYING THE GAME", "sharpsignalDocId": 459}, {"page": 6, "score": 0.030769, "snippet": "put role placards back in the middle of the table governor changes - and reminds owners of the chapel checks players' hands for the card limit (7 or 12) begin the new round * Important: the number of cards in a player's hand is always available to other players. The content, of course, is not. as so", "headingPath": "the following rounds:", "sharpsignalDocId": 459}, {"page": 3, "score": 0.030303, "snippet": "offers each player one action (exception: prospector) gives a special privilege to the player who chose the role Builder phase: each player may build one building; the builder pays 1 card less During play, the players discard cards face down to the discard stack. Because both the card supply and the", "headingPath": "Each role", "sharpsignalDocId": 459}, {"page": 3, "score": 0.029851, "snippet": "Each role has an associated action (phase) for all players, taken in clockwise order, and a special privilege only for the player who selected the role (exception: prospector) . Basically: The player selecting the role is the first to take the associated action. The other players follow in clockwise", "headingPath": "The roles · Builder (builder phase ❖☎ all build a building) · Note:", "sharpsignalDocId": 459}, {"page": 5, "score": 0.029412, "snippet": "The special functions of several buildings may allow a player to alter these selling rules if he has the building in his play area when he sells. These include the market stand, the trading post, the market hall, and the library. The players may choose to take their actions simultaneously as there i", "headingPath": "Note: · Prospector (prospector phase ❖☎ no action)", "sharpsignalDocId": 459}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "PREPARATION", "sharpsignalDocId": 459}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 459 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 459 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 7, 2026 05:48
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 San Juan — Rulebook (corpus doc 459) | PREPARATION | p.2 | 0.032787 (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 San Juan — Rulebook (corpus doc 459) | Each role · Note: | p.4 | 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 San Juan — Rulebook (corpus doc 459) | A new round · GAME END · The buildings | p.6 | 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 San Juan — Rulebook (corpus doc 459) | PLAYING THE GAME | p.2 | 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 San Juan — Rulebook (corpus doc 459) | the following rounds: | p.6 | 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 San Juan — Rulebook (corpus doc 459) | Each role | p.3 | 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 San Juan — Rulebook (corpus doc 459) | The roles · Builder (builder phase ❖☎ all build a building) · Note: | p.3 | 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 San Juan — Rulebook (corpus doc 459) | Note: · Prospector (prospector phase ❖☎ no action) | p.5 | 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
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 San Juan — Rulebook (corpus doc 459) | PREPARATION | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 225 ms · first delta 4114 ms · total 5643 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 225 ms · ask 5410 ms · gateway work 5643 ms · total 5643 ms
- tokens in (the prompt the answerer read)
- 3954
- tokens out (what the answerer generated)
- 197
- tok/sec
- 135.5 tok/sec — 197 output tokens in 1.454 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s 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
- 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 389), 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.