Ruling — At the Gates of Loyang

You asked

When does the game end?

Answered counted as answered

Asked with: At the Gates of Loyangbg-39683-en-1e

The game ends after 9 Rounds,[1] which is at the end of the Round in which players finish harvesting their Home field.[1]

[1] RULEBOOK At the Gates of Loyang — Rulebook · p.8 · End of the Game · Notes and Special cases: · Frequently Asked Questions

🔧 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 72 ms · ask 3939 ms · total 4013 ms
single-flight (PR-5): queued 0 ms · generation 4013 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 8, "score": 0.04918, "snippet": "The Game ends after 9 Rounds - that is, at the end of the Round in which players finish harvesting their Home field. Players who have taken Loans must now move their Scoring marker back 1 space along the Path of Prosperity for each Loan card that they have. T he winner is the player whose Scoring ma", "headingPath": "End of the Game · Notes\tand\tSpecial\tcases: · Frequently Asked Questions", "sharpsignalDocId": 462}, {"page": 4, "score": 0.048131, "snippet": "A player’s last card may never be placed in the Courtyard; it must be played from his hand. There is no limit to the number of cards that may be placed in any row of a player’s play area. At the end of the Distribution round, the remaining cards in the Courtyard form a new face-up Discard pile. They", "headingPath": "", "sharpsignalDocId": 462}, {"page": 7, "score": 0.046898, "snippet": "At the end of each turn, players move leftover vegetables from their Cart to their Storehouse. A player can only hold as many vegetables as are shown on his Storehouse: any additional vegetables must be sold to his Shop or discarded (returned to the Supply). A Storehouse with a capacity of only 1 ve", "headingPath": "Store\tVegetables · Players\tpay\tCash\tto\tprogress\talong\tthe\tPath\tof\tProsperity. · Loans · Notes\tand\tspecial\tcases:", "sharpsignalDocId": 462}, {"page": 4, "score": 0.045688, "snippet": "D uring the Distribution round, at the start of his turn, a player may choose to turn over the top Action card from the Draw pile and place it in the Courtyard. (This is also allowed when only one player is left and he must immediately choose from the available cards. This special rule gives players", "headingPath": "Special\trules\tfor\t2\tplayers: · Important: · Notes\tand\tSpecial\tCases: · Choose\ta\tnew\tstarting\tplayer · Special\trules\tfor\tthe\tFour-player\tgame", "sharpsignalDocId": 462}, {"page": 4, "score": 0.045476, "snippet": "The Starting and Second players take their Action phase at the same time. Once they have finished, their partners can have their turns. Note: Whenever a player takes an action that refers explicitly to “the other players”, only the player’s current partner may be affected. Cards which allow this typ", "headingPath": "", "sharpsignalDocId": 462}, {"page": 9, "score": 0.031746, "snippet": "The Solo game takes around 1 hour. It works exactly the same as the game for 2 to 4 players, with the following additions: Shuffle the Action cards. For an imaginary opponent, turn over cards until there are exactly 2 Market stalls, 2 Regular customers and 2 Casual customers. Fill the Market stalls ", "headingPath": "Solo game · Preparation: · Card phase: · Your\tGoal:", "sharpsignalDocId": 462}, {"page": 3, "score": 0.03125, "snippet": "The game is played over 9 Rounds . Each Round consists of 3 Phases : Harvest phase (players receive one new field and harvest vegetables from their fields) Card phase (players each play 2 Action cards, then a new Starting player is chosen) Action phase (players buy and sell vegetables, then progress", "headingPath": "Playing the game · Phase 1: Harvest phase · Phase 2: Card phase", "sharpsignalDocId": 462}, {"page": 6, "score": 0.029412, "snippet": "Fill the Regular customer card from the bottom to the top . The arrows between the prices are a reminder of this. When a player makes a delivery to a Regular customer, he receives the payment for the delivery immediately. Players may not partially fill a row (that is, only supply 1 vegetable). A Reg", "headingPath": "Notes\tand\tSpecial\tcases:", "sharpsignalDocId": 462}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 8, "quote": null, "headingPath": "End of the Game · Notes\tand\tSpecial\tcases: · Frequently Asked Questions", "sharpsignalDocId": 462}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 462 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 462 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 11, 2026 20:54

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 At the Gates of Loyang — Rulebook (corpus doc 462)	End of the Game · Notes and Special cases: · Frequently Asked Questions	p.8	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)		p.4	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 At the Gates of Loyang — Rulebook (corpus doc 462)	Store Vegetables · Players pay Cash to progress along the Path of Prosperity. · Loans · Notes and special cases:	p.7	0.046898 (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 At the Gates of Loyang — Rulebook (corpus doc 462)	Special rules for 2 players: · Important: · Notes and Special Cases: · Choose a new starting player · Special rules for the Four-player game	p.4	0.045688 (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 At the Gates of Loyang — Rulebook (corpus doc 462)		p.4	0.045476 (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 At the Gates of Loyang — Rulebook (corpus doc 462)	Solo game · Preparation: · Card phase: · Your Goal:	p.9	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
#7	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Playing the game · Phase 1: Harvest phase · Phase 2: Card phase	p.3	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
#8	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Notes and Special cases:	p.6	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 35 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 At the Gates of Loyang — Rulebook (corpus doc 462)	End of the Game · Notes and Special cases: · Frequently Asked Questions	p.8	#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 At the Gates of Loyang — Rulebook (corpus doc 462)		p.4	#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
#3	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Helper Reference	p.12	#32	0.01087 (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
#4	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)		p.4	#5	0.045476 (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
#5	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Solo game · Preparation: · Card phase: · Your Goal:	p.9	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Playing the game · Phase 1: Harvest phase · Phase 2: Card phase	p.3	#7	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
#7	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Helper Reference	p.12	#18	0.012821 (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
#8	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	Store Vegetables · Players pay Cash to progress along the Path of Prosperity. · Loans · Notes and special cases:	p.7	#3	0.046898 (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

#	document	heading	page	quote chars
[1]	RULEBOOK At the Gates of Loyang — Rulebook (corpus doc 462)	End of the Game · Notes and Special cases: · Frequently Asked Questions	p.8	no quote on the wire

generation — timing and the path taken

timing split: retrieval 72 ms · first delta 3720 ms · total 4013 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 72 ms · ask 3939 ms · gateway work 4013 ms · total 4013 ms
tokens in (the prompt the answerer read): 3670
tokens out (what the answerer generated): 30
tok/sec: 138.9 tok/sec — 30 output tokens in 0.216 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: 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 392), 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.