Ruling — Ankh: Gods of Egypt

You asked

When does the game end?

Answered counted as answered

Asked with: Ankh: Gods of Egyptbg-285967-en-1e

The game ends in one of the following ways:

1. A player wins immediately when their Ankh token reaches the top space of the Devotion track.[1]

2. A player wins immediately if they are the only god left in play after the 4th Conflict event.[1] (If no gods are left in play at this stage, the game ends in a draw and Egypt becomes atheistic).[1]

3. If neither of the previous conditions are met, the game is won by the player with the most Devotion after the last Event on the track is resolved.[1]

[1] RULEBOOK Ankh: Gods of Egypt — Rulebook · p.13 · BATTLE CARDS

🔧 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 77 ms · ask 4027 ms · total 4105 ms
single-flight (PR-5): queued 0 ms · generation 4105 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 27, "score": 0.048916, "snippet": "FORGOTTEN GODS Towards the end of the game, at the end of the 4 th Conflict event, any gods with their Ankh token still in the red section of the Devotion track are forgotten by the people of Egypt and eliminated from the game. Remove the forgotten gods' figures (God, Warriors, and Guardians) from t", "headingPath": "Merged God Gameplay", "sharpsignalDocId": 358}, {"page": 13, "score": 0.048652, "snippet": "Follow any Additional Setup Rules as dictated in the scenario book. 12 You are ready to play! There are 3 ways to become the only God of Egypt and win the game: A player wins immediately when their Ankh token reaches the top space of the Devotion track. A player wins immediately if they are the only", "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 11, "score": 0.046875, "snippet": "Devotion is the measure of how much a god is worshipped by the people of Egypt. Each god's current Devotion level is marked with an Ankh token on the Devotion dashboard. Each god begins the game at the bottom of the Devotion track (the lowest red space), and as they earn more Devotion, their Ankh to", "headingPath": "DEVOTION · BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 9, "score": 0.046154, "snippet": "During the game, players take turns performing actions including moving their figures on the board to seize control of key territory, summoning Warriors and Guardians to battle their opponents, gaining new Followers, and unlocking new Ankh powers. The 4 possible actions are depicted on the top half ", "headingPath": "CENTRAL DASHBOARD", "sharpsignalDocId": 358}, {"page": 25, "score": 0.045285, "snippet": "Only in a game with 3 or more players , at the end of the 3 rd Conflict, the 2 gods with the least Devotion (the ones in the bottom 2 positions in the Devotion track) are at risk of being forgotten by the people of Egypt. To avoid that fate, those 2 gods merge into a single divine entity. The player", "headingPath": "MERGING GODS", "sharpsignalDocId": 358}, {"page": 32, "score": 0.031746, "snippet": "The player who triggered the event takes the Battle Tiebreaker token. Then, check each region in order: Domination (One Player): Gain 1 Devotion for each Monument majority you have. Then, gain 1 Devotion for dominating the region. Battle (Multiple Players): Disregard players, figures, and Monuments ", "headingPath": "Conflict:", "sharpsignalDocId": 358}, {"page": 24, "score": 0.030303, "snippet": "All players with figures in the region calculate their total strength in the Battle. Each figure provides 1 strength, but individual Guardian abilities, God powers, or Ankh powers might increase this amount. Each Battle card also has a bonus strength value which is added to that player's total (as l", "headingPath": "5. Battle Resolution", "sharpsignalDocId": 358}, {"page": 19, "score": 0.029851, "snippet": "As the struggle between the gods unfolds, momentous events mark the passage of time. Monuments are erected, caravans divide the land, and violent conflicts change the balance of power. All of these events are represented on the Event track, which serves as the game's timeline. When an Action marker ", "headingPath": "Controlling Guardians", "sharpsignalDocId": 358}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 13, "quote": null, "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 358 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 358 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 0.93052 of 403 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 12, 2026 13:46

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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	Merged God Gameplay	p.27	0.048916 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	BATTLE CARDS	p.13	0.048652 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	DEVOTION · BATTLE CARDS	p.11	0.046875 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	CENTRAL DASHBOARD	p.9	0.046154 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	MERGING GODS	p.25	0.045285 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	Conflict:	p.32	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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	5. Battle Resolution	p.24	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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	Controlling Guardians	p.19	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

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 50 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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	Merged God Gameplay	p.27	#1	0.048916 (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
#2	RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358)	MERGING GODS	p.25	#5	0.045285 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	DEVOTION · BATTLE CARDS	p.11	#3	0.046875 (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
#4	RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358)	CENTRAL DASHBOARD	p.9	#4	0.046154 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	CAT-MUMMY · SATET · APEP · MUMMY · GIANT SCORPION	p.31	#12	0.025914 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	TABLE OF CONTENTS · FREE DIGITAL CONTENT	p.2	#13	0.025038 (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
#7	RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358)		p.2	#41	0.009901 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	BATTLE CARDS	p.13	#2	0.048652 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358)	BATTLE CARDS	p.13	no quote on the wire

generation — timing and the path taken

timing split: retrieval 77 ms · first delta 3247 ms · total 4105 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 77 ms · ask 4027 ms · gateway work 4105 ms · total 4105 ms
tokens in (the prompt the answerer read): 2950
tokens out (what the answerer generated): 124
tok/sec: 149.4 tok/sec — 124 output tokens in 0.830 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 43s 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 287), 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.