Ruling — Marrakesh

You asked

How do I play?

Answered counted as answered

Asked with: Marrakeshbg-342810-en-1e

Marrakesh is played over 3 seasons with 4 rounds each.[1] Each round is divided into 4 phases:[1]

1. All players simultaneously select 3 hidden keshis from behind their screen and hold them in their hand.[1]

2. Once all players have selected, they show their selection openly and deploy their 3 assistants to the sectors of their player board matching the colors of their selected keshis.[1]

3. One player takes all selected keshis from all players and tosses them into the cube tower all at once.[1]

4. After players sort the keshis in the tower's base by color, they split the keshis among themselves in turn order.[1]

5. Players take turns claiming up to 2 keshis of a single color at a time, placing them immediately on the corresponding sector of their player board, continuing until all keshis from the tower's base have been claimed and deployed.[1]

In turn order, each player uses their 3 assistants in any order they like, choosing between one of two options for each assistant:[1]

* Take one keshi of the corresponding sector's color from the common supply and deploy it (gaining the deployment bonus if applicable).[1]

* Perform that sector action.[1] (Note: If a red water vendor was deployed in that sector during a previous turn, the player first gains 1 water).[1]

[1] RULEBOOK Marrakesh — Rulebook · p.6 · PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)

🔧 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 5745 ms · total 5819 ms
single-flight (PR-5): queued 0 ms · generation 5819 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 6, "score": 0.04918, "snippet": "The following is a general outline of how to play the game. Later on, you may refer to it to look up the most important rules and to fi nd the corresponding rules pages. Marrakesh is played over 3 seasons with 4 rounds each: The player holding the round counter (camel) is the start player during the", "headingPath": "PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)", "sharpsignalDocId": 452}, {"page": 4, "score": 0.047183, "snippet": "Place the game board in the center of the playing area. Put the cube tower base next to the game board and insert the cube tower in the provided slot. Keep the \"100/200\" scoring tiles next to the scoring track. When a player completes a full round on the scoring track, they take the tile in their pl", "headingPath": "General Components · Player components", "sharpsignalDocId": 452}, {"page": 7, "score": 0.046032, "snippet": "Each round consists of the following 4 phases, which are played in sequence: U Select keshis & deploy assistants U Claim keshis & deploy them U Use your assistants U River bonus & end of the round The player holding the round counter is the start player during the complete round. Simultaneously, all", "headingPath": "ROUND SEQUENCE · U Select keshis & deploy assistants · Claim keshis & deploy them", "sharpsignalDocId": 452}, {"page": 14, "score": 0.03125, "snippet": "Discard the exchange offi ce tile from the game board. Reveal the next exchange offi ce, which will be the active offi ce for the next season. Place the river tile for the next season on the end of the river track. Again, each player takes 1 keshi of each color (12 in total) from the common supply a", "headingPath": "Preparing the 2nd and 3rd season: · END OF THE GAME AND FINAL SCORING · 1) Completely fi lled sectors: · 2) Oasis tiles:", "sharpsignalDocId": 452}, {"page": 21, "score": 0.030769, "snippet": "Gain or take something Return something to the common supply or discard Use something Gain [1] point Lose [3] points Any resource (dinar, date, water) Keshi (of the depicted color) Any keshi Any keshi (except goods keshis) Goods keshi (yellow, orange, purple) Deploy keshi (of the depicted color) fro", "headingPath": "SUMMARY OF ıCONS · ADDENDUM", "sharpsignalDocId": 452}, {"page": 21, "score": 0.030303, "snippet": "1 S/U.sc/M.sc/M.sc/A.sc/R.sc/Y.sc /O.sc/F.sc /dotlessi.sc/C.sc/O.sc/N.sc/S.sc Gain or take something Return something to the common supply or discard Use something Gain [1] point Lose [3] points Any resource (dinar, date, water) Keshi (of the depicted color) Any keshi Any keshi (except goods keshis)", "headingPath": "", "sharpsignalDocId": 452}, {"page": 10, "score": 0.029851, "snippet": "In the madrasa players can acquire scrolls . The top left corner of a scroll indicates the minimum number of gray scholars the player needs to have deployed in their madrasa to acquire the scroll (1, 3, 5, or 7). Additionally, the player must pay up to 3 dates (as shown on the top right corner ). Th", "headingPath": "Madrasa", "sharpsignalDocId": 452}, {"page": 5, "score": 0.029412, "snippet": "Sort the river tiles by their season icons and put them separately in the cloth bag, one season after the other. Randomly draw 1 tile per season. Place the 3 drawn tiles next to the game board with any side up, which will be the active side during the game. Place the river tile for the fi rst season", "headingPath": "Player components", "sharpsignalDocId": 452}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 6, "quote": null, "headingPath": "PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)", "sharpsignalDocId": 452}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 452 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 452 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 0.92568 of 1063 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 15, 2026 05:35

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 Marrakesh — Rulebook (corpus doc 452)	PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)	p.6	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	General Components · Player components	p.4	0.047183 (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 Marrakesh — Rulebook (corpus doc 452)	ROUND SEQUENCE · U Select keshis & deploy assistants · Claim keshis & deploy them	p.7	0.046032 (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 Marrakesh — Rulebook (corpus doc 452)	Preparing the 2nd and 3rd season: · END OF THE GAME AND FINAL SCORING · 1) Completely fi lled sectors: · 2) Oasis tiles:	p.14	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 Marrakesh — Rulebook (corpus doc 452)	SUMMARY OF ıCONS · ADDENDUM	p.21	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 Marrakesh — Rulebook (corpus doc 452)		p.21	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 Marrakesh — Rulebook (corpus doc 452)	Madrasa	p.10	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 Marrakesh — Rulebook (corpus doc 452)	Player components	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

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 59 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 Marrakesh — Rulebook (corpus doc 452)	PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)	p.6	#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 Marrakesh — Rulebook (corpus doc 452)	GAME COMPONENTS: · Changes in SETUP : · Changes in GAME PLAY : · GAME COMPONENTS	p.16	#11	0.028283 (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
#3	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	Madrasa	p.11	#17	0.014286 (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 Marrakesh — Rulebook (corpus doc 452)	Changes in GAME PLAY : · Changes in SCORING: · Changes in SETUP : · 2 Covering tiles per player	p.17	#15	0.026999 (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
#5	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	Preparing the 2nd and 3rd season: · END OF THE GAME AND FINAL SCORING · 1) Completely fi lled sectors: · 2) Oasis tiles:	p.14	#4	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
#6	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	Mosque and palace · Example: · Summary of line bonuses between the mosque and palace staircases:	p.10	#30	0.011236 (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
#7	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	Player components	p.5	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Marrakesh — Rulebook (corpus doc 452)	General Components · Player components	p.4	#2	0.047183 (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 Marrakesh — Rulebook (corpus doc 452)	PLAYING THE GAME · Select keshis & deploy assistants (p. 7) · U Claim keshis & deploy them (p. 7) · U Use your assistants (p. 8)	p.6	no quote on the wire

generation — timing and the path taken

timing split: retrieval 72 ms · first delta 3596 ms · total 5819 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 5745 ms · gateway work 5819 ms · total 5819 ms
tokens in (the prompt the answerer read): 3679
tokens out (what the answerer generated): 308
tok/sec: 141.3 tok/sec — 308 output tokens in 2.179 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 39s 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 377), 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.