RuleSage cited table rulings
← Abyss

You asked

When does the game end?

Answered counted as answered

Asked with: Abyssbg-155987-en-1e

The game ends when either of the following occurs:
* Any player recruits their 7th Lord.[1]
* Any player recruits a Lord and the Court needs to be refilled, but there are not enough Lord cards left to completely fill the Court.[1]
[1] RULEBOOK Abyss — Rulebook · p.10 · The End of your Turn · The End of the Game
🔧 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 97 ms · ask 2077 ms · total 2179 ms
single-flight (PR-5)
queued 0 ms · generation 2179 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
[{"page": 10, "score": 0.04918, "snippet": "When you have finished your mandatory actions, your turn is over. The player to your left now begins their turn, following the same steps as above. Players continue taking turns until one of the end-of-the-game conditions is met. The game ends when either of the following occurs: Any player recruits", "headingPath": "The End of your Turn · The End of the Game", "sharpsignalDocId": 486}, {"page": 11, "score": 0.047371, "snippet": "With their locations the player wins 32 Influence Points: due to the Parliament, the player wins 6 IP, plus 2 IP for each politician Lord they've recruited. They have two politician Lords, for a total of 10 IP. due to the Sanctuary, the player gains 4 IP, plus 3 IP for each Ally of the jellyfish Rac", "headingPath": "The End of the Game", "sharpsignalDocId": 486}, {"page": 12, "score": 0.046635, "snippet": "Affiliate: keep in front of you the weakest Ally used during a recruitment. Ally: card from the Exploration deck which represents a squid, a seahorse, a shell, a jellyfish, or a crab, with a value of 1 to 5. Council: area of the board where, Race by Race, the Allies who were not kept during the Expl", "headingPath": "The End of the Game · Monster: · Threat:", "sharpsignalDocId": 486}, {"page": 4, "score": 0.045724, "snippet": "To be crowned King of Abyss you must have the most Influence Points ('IP') at the end of the game. Influence Points are mainly gained by affiliating Allies, recruiting Lords, and controlling Locations. Also, each Monster you slay during the game will earn you the gratitude of your peers-and an Influ", "headingPath": "Object of the Game · Game Overview", "sharpsignalDocId": 486}, {"page": 6, "score": 0.032258, "snippet": "Once you have decided to either add an Ally to your hand or fight a Monster, your turn ends. All Allies that remain on the Exploration Track are placed, face down, on the spaces matching their Race in the part of the board called the 'Council'. Any Monsters are placed in the Exploration discard pile", "headingPath": "End of Exploration: · Request Support From the Council", "sharpsignalDocId": 486}, {"page": 5, "score": 0.030769, "snippet": "Then, they reveal a 4th card, which is bought by the 1st opponent for 2 Peals, as it's the 2nd Ally purchased this turn. Then the active player reveals 3 more cards that their opponents turn down or can no longer afford and which does not interest the active player either. But the 7th revealed card ", "headingPath": "If the revealed card is a Monster:", "sharpsignalDocId": 486}, {"page": 5, "score": 0.030303, "snippet": "You must either FIGHT THE MONSTER or KEEP EXPLORING. If you decide to fight, victory is automatic and the Monster is discarded. You win the reward shown on the Threat Track, which may include: P e a r l s taken from the Treasury; Influence Points from a randomly drawn Monster token down); Keys . Som", "headingPath": "If the revealed card is a Monster:", "sharpsignalDocId": 486}, {"page": 9, "score": 0.030018, "snippet": "Control Locations As soon as you gather three Keys (Keys are gained when you recruit a Lord with a Key symbol or by fighting a Monster while Exploration) you must immediately take control of a Location. 3 On Location cards, you will find: The name of the Location Which gives an indication on how to ", "headingPath": "Refill the Court: · A symbol :", "sharpsignalDocId": 486}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
[{"page": 10, "quote": null, "headingPath": "The End of your Turn · The End of the Game", "sharpsignalDocId": 486}]
boost provenance — errata + base rulebook (E2/E3)
no registered errata card matched this query; base rulebook doc 486 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 486 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 0.93122 of 189 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until
Nov 15, 2026 22:23

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 rankdocumentheadingpage fused RRF scoresnippet chars
#1 RULEBOOK Abyss — Rulebook (corpus doc 486) The End of your Turn · The End of the Game p.10 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) 300
#2 RULEBOOK Abyss — Rulebook (corpus doc 486) The End of the Game p.11 0.047371 (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 Abyss — Rulebook (corpus doc 486) The End of the Game · Monster: · Threat: p.12 0.046635 (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 Abyss — Rulebook (corpus doc 486) Object of the Game · Game Overview p.4 0.045724 (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 Abyss — Rulebook (corpus doc 486) End of Exploration: · Request Support From the Council p.6 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
#6 RULEBOOK Abyss — Rulebook (corpus doc 486) If the revealed card is a Monster: p.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)) 300
#7 RULEBOOK Abyss — Rulebook (corpus doc 486) If the revealed card is a Monster: p.5 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 Abyss — Rulebook (corpus doc 486) Refill the Court: · A symbol : p.9 0.030018 (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 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 16 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 atdocumentheadingpage fused rankfused RRF scorecarried byhow it got its slot
#1 RULEBOOK Abyss — Rulebook (corpus doc 486) The End of your Turn · The End of the Game p.10 #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 Abyss — Rulebook (corpus doc 486) The End of the Game · Monster: · Threat: p.12 #3 0.046635 (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 Abyss — Rulebook (corpus doc 486) Refill the Court: · A symbol : p.9 #8 0.030018 (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 re-ranker chose it
#4 RULEBOOK Abyss — Rulebook (corpus doc 486) End of Exploration: · Request Support From the Council p.6 #5 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
#5 RULEBOOK Abyss — Rulebook (corpus doc 486) Clarifications p.12 #10 0.02885 (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 re-ranker chose it
#6 RULEBOOK Abyss — Rulebook (corpus doc 486) If the revealed card is a Monster: p.5 #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)) vector + the doc-priority boost arm the re-ranker chose it
#7 RULEBOOK Abyss — Rulebook (corpus doc 486) Object of the Game · Game Overview p.4 #4 0.045724 (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
#8 RULEBOOK Abyss — Rulebook (corpus doc 486) The End of the Game p.11 #2 0.047371 (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

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.

#documentheadingpagequote chars
[1] RULEBOOK Abyss — Rulebook (corpus doc 486) The End of your Turn · The End of the Game p.10 no quote on the wire
timing split
retrieval 97 ms · first delta 1865 ms · total 2179 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 97 ms · ask 2077 ms · gateway work 2179 ms · total 2179 ms
tokens in (the prompt the answerer read)
3178
tokens out (what the answerer generated)
56
tok/sec
205.9 tok/sec — 56 output tokens in 0.272 s of generation
live seat (read from the running child)
answering — gemma4:26b think:false · num_ctx 32768 (live-verified 6s 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.
outcome
ANSWERED — Answered
abstain rationale (n/a — this ruling answered)
answered — no abstain rationale applies
decision
NOT_SETUP_SHAPED — no setup-shape pattern matched this question

this game registers NO errata cards (edition 417), 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.