Ruling — Azul: Master Chocolatier

You asked

How do I play?

Answered counted as answered

Asked with: Azul: Master Chocolatierbg-363247-en-1e

The game is played over multiple rounds, each consisting of three phases: Factory offer, Box confection, and Preparing the next round.[1]

**1. Factory offer**

1. The starting player places the starting player marker in the center of the table and takes the first turn.[1]

2. Play continues clockwise.[1]

3. On your turn, you must pick tiles in one of two ways:

* Pick all tiles of the same color from any one Factory display and then move the remaining tiles from this Factory display to the center of the table.[1]

* Pick all tiles of the same color from the center of the table.[1]

4. If you are the first player in the round to pick tiles from the center of the table, take the starting player marker and place it onto the leftmost free space of your foundry line.[1]

5. Add the tiles you picked to one of the 5 pattern lines on your player board (the first line has 1 space and the fifth has 5).[1]

6. Place the tiles, one by one, from right to left in your chosen pattern line.[1]

7. If the pattern line already holds tiles, you may only add tiles of the same color to it.[1]

8. If you pick up more tiles than you can place in your chosen pattern line, you must place the excess tiles in the foundry line.[1]

9. This phase ends when the center of the table and all Factory displays contain no more tiles.[2]

**2. Box confection**

1. This phase can be carried out by all players simultaneously.[3][4]

2. Go through your pattern lines from top to bottom.[3][4]

3. Move the rightmost tile of each complete line to the space of the same color in the corresponding line of your chocolate box.[3][4]

4. Score points immediately each time you move a tile.[3][4]

5. Remove all tiles from any pattern lines that now have no tile in the rightmost space and place them into the lid of the game box.[3][4]

6. Any remaining tiles on the pattern lines stay on your player board for the next round.[3]

**3. Preparing the next round**

1. If nobody has completed a horizontal line of 5 consecutive tiles in their chocolate box yet, prepare the next round.[5]

2. The player with the starting player marker refills each Factory display with 4 tiles from the bag.[5]

3. If the bag is empty, refill it with all tiles placed in the lid of the game box and continue filling the remaining Factory displays.[5]

4. Start the new round.[5]

**Scoring**

* **During Box confection:** Each tile moved to the chocolate box is placed on the space matching its color and scores as follows:

* If there are no tiles directly adjacent (vertically or horizontally) to the newly placed tile, gain 1 point.[5]

* If there are horizontally linked tiles, count all these linked tiles (including the newly placed one) and gain that many points.[5]

* If there are vertically linked tiles, count all these linked tiles (including the newly placed one) and gain that many points.[5]

* **At the end of the Box confection phase:**

* For each tile in your foundry line, lose the number of points indicated directly above it (adjusting your score tracker, but never dropping below 0).[5]

* **End of game bonus points:**

* Gain 2 points for each complete horizontal line of 5 consecutive tiles in your chocolate box.[6]

* Gain 7 points for each complete vertical line of 5 consecutive tiles in your chocolate box.[6]

* Gain 10 points for each color of which you have placed all 5 tiles in your chocolate box.[6]

**End of the Game**

The game ends right after the Box confection phase in which at least one player has completed at least one horizontal line of 5 consecutive tiles in their chocolate box.[6] The player with the most points on their score track wins.[6] In the case of a tie, the tied player with more complete horizontal lines wins; if the tie is still not broken, the victory is shared.[6]

[1] RULEBOOK Azul: Master Chocolatier — Rulebook · p.2 · Object of the game · Gameplay · A. Factory offer · First turns example

[2] RULEBOOK Azul: Master Chocolatier — Rulebook · p.3

[3] RULEBOOK Azul: Master Chocolatier — Rulebook · p.3

[4] RULEBOOK Azul: Master Chocolatier — Rulebook · p.3 · B. Box confection

[5] RULEBOOK Azul: Master Chocolatier — Rulebook · p.4 · Scoring · C. Preparing the next round

[6] RULEBOOK Azul: Master Chocolatier — Rulebook · p.5 · End of the game · Variant play

That settles it — whose turn was it?

🔧 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 83 ms · ask 5814 ms · total 8653 ms
single-flight (PR-5): queued 2754 ms · generation 5899 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 1, "score": 0.04918, "snippet": "Give each player a player board (A) . Flip your board to the side with the colored chocolate box. (See Variant Play to play with the brown side of the player board). Each player must use the same side. Take 1 scoring marker (B) and place it on space '0' of your score track. Place the Factory display", "headingPath": "Game Setup", "sharpsignalDocId": 660}, {"page": 2, "score": 0.048387, "snippet": "To be the player with the most points at the end of the game. The game ends after the round in which at least one player has completed a horizontal line of 5 consecutive tiles in their chocolate box. The game is played over multiple rounds, each of which is composed of three phases: Factory offer Bo", "headingPath": "Object of the game · Gameplay · A. Factory offer · First turns example", "sharpsignalDocId": 660}, {"page": 5, "score": 0.046642, "snippet": "The game ends right after the Box confection phase in which at least one player has completed at least one horizontal line of 5 consecutive tiles in their chocolate box. Once the game has ended, score additional points if you have achieved the following goals: Gain 2 points for each complete horizon", "headingPath": "End of the game · Variant play", "sharpsignalDocId": 660}, {"page": 5, "score": 0.045037, "snippet": "At the beginning of the game and at the beginning of phase C, shuffle all 9 Factory displays, blue side visible. Then, place a certain number of these according to the setup rules. Finally, randomly flip a number of Factory displays equal to the number of players, revealing the gold side of the Spec", "headingPath": "Special Factories variant · Development by:", "sharpsignalDocId": 660}, {"page": 3, "score": 0.031746, "snippet": "This phase can be carried out by all players simultaneously, as they move tiles from their complete pattern lines over to their chocolate box. Go through your pattern lines from top to bottom . Move the rightmost tile of each complete line to the space of the same color in the corresponding line of ", "headingPath": "B. Box confection", "sharpsignalDocId": 660}, {"page": 3, "score": 0.03125, "snippet": "• If the pattern line already holds tiles, you may only add tiles of the same color to it. • Once all spaces of a pattern line are filled, that line is considered complete. If you have picked up more tiles than you can place in your chosen pattern line, you must place the excess tiles in the foundry", "headingPath": "", "sharpsignalDocId": 660}, {"page": 4, "score": 0.030303, "snippet": "Each tile you move over to your chocolate box is always placed on the space matching its color and immediately scores as follows: If there are no tiles directly adjacent (vertically or horizontally) to the newly placed tile, gain 1 point on the score track. If there are any tiles adjacent, however, ", "headingPath": "Scoring · C. Preparing the next round", "sharpsignalDocId": 660}, {"page": 3, "score": 0.029851, "snippet": "From his complete fourth pattern line, he moves the rightmost teal From his complete fourth pattern line, he moves the rightmost teal tile over to the teal space in the chocolate box tile over to the teal space in the chocolate box (and scores 1 point immediately).(and scores 1 point immediately). H", "headingPath": "", "sharpsignalDocId": 660}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "Object of the game · Gameplay · A. Factory offer · First turns example", "sharpsignalDocId": 660}, {"page": 3, "quote": null, "headingPath": "", "sharpsignalDocId": 660}, {"page": 3, "quote": null, "headingPath": "", "sharpsignalDocId": 660}, {"page": 3, "quote": null, "headingPath": "B. Box confection", "sharpsignalDocId": 660}, {"page": 4, "quote": null, "headingPath": "Scoring · C. Preparing the next round", "sharpsignalDocId": 660}, {"page": 5, "quote": null, "headingPath": "End of the game · Variant play", "sharpsignalDocId": 660}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 660 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 660 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 0.91012 of 3082 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 25, 2026 20:49 UTC

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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Game Setup	p.1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	Object of the game · Gameplay · A. Factory offer · First turns example	p.2	0.048387 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	End of the game · Variant play	p.5	0.046642 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Special Factories variant · Development by:	p.5	0.045037 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	B. Box confection	p.3	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
#6	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)		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
#7	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	Scoring · C. Preparing the next round	p.4	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 Azul: Master Chocolatier — Rulebook (corpus doc 660)		p.3	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 11 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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Game Setup	p.1	#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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	End of the game · Variant play	p.5	#3	0.046642 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Scoring · C. Preparing the next round	p.4	#7	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))	vector + the doc-priority boost arm	the re-ranker chose it
#4	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)		p.3	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)		p.3	#6	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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Special Factories variant · Development by:	p.5	#4	0.045037 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	B. Box confection	p.3	#5	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
#8	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	Object of the game · Gameplay · A. Factory offer · First turns example	p.2	#2	0.048387 (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 Azul: Master Chocolatier — Rulebook (corpus doc 660)	Object of the game · Gameplay · A. Factory offer · First turns example	p.2	no quote on the wire
[2]	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)		p.3	no quote on the wire
[3]	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)		p.3	no quote on the wire
[4]	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	B. Box confection	p.3	no quote on the wire
[5]	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	Scoring · C. Preparing the next round	p.4	no quote on the wire
[6]	RULEBOOK Azul: Master Chocolatier — Rulebook (corpus doc 660)	End of the game · Variant play	p.5	no quote on the wire

generation — timing and the path taken

timing split: retrieval 83 ms · first delta 1254 ms · total 8653 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 2754 ms · retrieval 83 ms · ask 5814 ms · gateway work 5899 ms · total 8653 ms
tokens in (the prompt the answerer read): 3522
tokens out (what the answerer generated): 922
tok/sec: 201.5 tok/sec — 922 output tokens in 4.576 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 53s ago)
gateway schema (read from the running child): schema head 0042_definer_search_path (live revision not readable by this principal)
answerer host (measured by rulesage): reachable (for 60h, checked 10s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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 593), 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.