Ruling — Mille Fiori

You asked

How do I play?

Answered counted as answered

Asked with: Mille Fioribg-346501-en-1e

1. Lay the playing board out in the middle of the table.[1]

2. Find the Doge card among the 110 cards and remove it from the pack.[1]

3. Shuffle the remaining cards and place them face down next to the playing board as a draw pile.[1]

4. Turn over a number of cards and place them face up next to the playing board based on the number of players: 9 cards for 2 and 4 players, or 4 cards for 3 players.[1]

5. Each player chooses a color and takes 30 transparent diamonds, 1 ship, and 1 points marker in that color.[1]

6. Place 27 diamonds in front of you as a personal supply and return 3 to the box.[1]

7. Place your ship on the starting space for the trade route and place your points marker on space 0 (100) of the points bar.[1]

8. The player with the fullest glass becomes the starting player and takes the Doge card.[1]

9. At the start of each round, the starting player deals five cards to each player turned face down.[2]

10. All players pick up their face down cards and select one card to keep in their hand.[2]

11. Place the remaining cards face down in front of your left-hand neighbor.[2]

12. The starting player begins and plays their hand card face up.[2]

13. In most cases, place one of your diamonds on an empty space in the color of the card just played.[2]

14. Immediately earn points for this and possibly additional bonuses, such as a point bonus and/or an extra card.[2]

15. Put your card face up on the discard pile (building one if there is no discard pile).[2]

16. The left-hand neighbor then takes their turn by playing their chosen card and placing a diamond appropriately.[2]

17. Once each player has played their chosen card in turn, pick up the cards in front of you, select one card to keep, and pass the remaining cards to your left-hand neighbor.[3]

18. Repeat this procedure until you have only one card left to pass on; do not pass this last card, but place it face up next to the playing board once all players have finished their turns.[3]

19. The starting player passes the Doge card to the next player (clockwise), who then becomes the new starting player for a new round.[3]

20. (For 2-player games only) Play only three out of five cards in each round by placing the last two cards face up next to the playing board and placing the last card in your hand face up next to the playing board.[3]

[1] RULEBOOK Mille Fiori — Rulebook · p.2

[2] RULEBOOK Mille Fiori — Rulebook · p.4 · How to Play the Game

[3] RULEBOOK Mille Fiori — Rulebook · p.5 · How to Play the Game · Th e game ends · Special Rule for the 2-Player 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 70 ms · ask 4350 ms · total 4422 ms
single-flight (PR-5): queued 0 ms · generation 4422 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 5, "score": 0.048652, "snippet": "Once each of you has played your chosen card in turn, pick up the cards in front of you. Select one card again from among these cards, exactly as described previously. Pass the remaining cards again to your left -hand neighbor and play your chosen card again in turn, beginning with the starting play", "headingPath": "How to Play the Game · Th e game ends · Special Rule for the 2-Player Game", "sharpsignalDocId": 626}, {"page": 4, "score": 0.047493, "snippet": "You play several rounds. At the start of each round, the starting player deals fi ve cards to each player turned face down . Now all players pick up their face down cards and select one card to keep in their hand. Place the remaining cards face down in front of your left hand neighbor. Th e starting", "headingPath": "How to Play the Game", "sharpsignalDocId": 626}, {"page": 9, "score": 0.046402, "snippet": "Whenever you help one of your fellow players to get a 'good deal' , you may immediately play an extra card. A deal is deemed good if at least one of your fellow players has more diamonds on this commodity than you do aft er you've placed your diamond (a tie is not suffi cient here). Y our fellow pla", "headingPath": "EXTRA CARD", "sharpsignalDocId": 626}, {"page": 2, "score": 0.046239, "snippet": "2 1. Lay the playing board out in the middle of the table. 2. First, /f_i nd the Doge card among the 110 cards and remove it from the pack. /T_h en shuﬄ e the remaining cards and place them face down next to the playing board as a draw pile. Depending on the number of players, turn over the number o", "headingPath": "", "sharpsignalDocId": 626}, {"page": 11, "score": 0.046154, "snippet": "In addition to a symbol, each card also features a value from 1 to 5 in the top corners. Instead of using the card as described previously, you may use any card to move forward on the sea route. In this case, you only use the number indicated and move your ship forward as many spaces on the sea rout", "headingPath": "Alternative Move · Note on the Extra Cards · Play Variations", "sharpsignalDocId": 626}, {"page": 10, "score": 0.045724, "snippet": "Whenever your ship lands on a space featuring the bonus symbol, you may immediately play an extra card. To do this, select one of the cards lying face up next to the playing board and play it exactly as if you had played it from your hand. So place one more diamond on the playing board, earn points ", "headingPath": "EXTRA CARD", "sharpsignalDocId": 626}, {"page": 12, "score": 0.044589, "snippet": "Th e game can end in one of two diff erent ways. ◆ When the starting player deals the last cards in the draw pile at the beginning of the round, you still play the round to the end. Th e game then ends aft er that. ◆ When you place your last diamond on the playing board during your turn, you fi nish", "headingPath": "End of the Game", "sharpsignalDocId": 626}, {"page": 3, "score": 0.043301, "snippet": "3 Card Features: GAME SETUP CARD COLOR: Shows which area of the playing board you may /f_i ll one space in. NUMBER IN THE SHIP’S WHEEL: Indicates how far you’re allowed to sail with your ship when you use the card to navigate the sea route. (Alternative move – page 11) SYMBOL: Determines which space", "headingPath": "", "sharpsignalDocId": 626}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 626}, {"page": 4, "quote": null, "headingPath": "How to Play the Game", "sharpsignalDocId": 626}, {"page": 5, "quote": null, "headingPath": "How to Play the Game · Th e game ends · Special Rule for the 2-Player Game", "sharpsignalDocId": 626}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 626 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 626 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 0.90669 of 1897 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 15, 2026 13:22

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 Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game · Th e game ends · Special Rule for the 2-Player Game	p.5	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
#2	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game	p.4	0.047493 (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 Mille Fiori — Rulebook (corpus doc 626)	EXTRA CARD	p.9	0.046402 (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 Mille Fiori — Rulebook (corpus doc 626)		p.2	0.046239 (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 Mille Fiori — Rulebook (corpus doc 626)	Alternative Move · Note on the Extra Cards · Play Variations	p.11	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
#6	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	EXTRA CARD	p.10	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
#7	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	End of the Game	p.12	0.044589 (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 Mille Fiori — Rulebook (corpus doc 626)		p.3	0.043301 (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 15 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 Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game	p.4	#2	0.047493 (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 Mille Fiori — Rulebook (corpus doc 626)	EXTRA CARD	p.10	#6	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
#3	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	EXTRA CARD	p.8	#10	0.030118 (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 Mille Fiori — Rulebook (corpus doc 626)	End of the Game	p.12	#7	0.044589 (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 Mille Fiori — Rulebook (corpus doc 626)	Workshops · PLACEMENT · INSTANT POINTS · POINT BONUS · EXTRA CARD · THE AREAS	p.6	#9	0.030415 (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 Mille Fiori — Rulebook (corpus doc 626)	EXTRA CARD	p.9	#3	0.046402 (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
#7	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)		p.2	#4	0.046239 (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 Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game · Th e game ends · Special Rule for the 2-Player Game	p.5	#1	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 Mille Fiori — Rulebook (corpus doc 626)		p.2	no quote on the wire
[2]	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game	p.4	no quote on the wire
[3]	RULEBOOK Mille Fiori — Rulebook (corpus doc 626)	How to Play the Game · Th e game ends · Special Rule for the 2-Player Game	p.5	no quote on the wire

generation — timing and the path taken

timing split: retrieval 70 ms · first delta 1492 ms · total 4422 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 70 ms · ask 4350 ms · gateway work 4422 ms · total 4422 ms
tokens in (the prompt the answerer read): 2894
tokens out (what the answerer generated): 599
tok/sec: 207.3 tok/sec — 599 output tokens in 2.889 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 37s 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 559), 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.