Ruling — Coloretto

You asked

How do I play?

Answered counted as answered

Asked with: Colorettobg-5782-en-1e

For 3 to 5 players:

1. Each player takes one summary card and chooses whether to play with the scoring table on the brown side or the violet side.[1]

2. Players place one brown row card in the middle of the table for each player in the game.[1]

3. Remove the 'last round' card from the deck and set it aside.[1]

4. Each player takes one card of a different color and places it in his play area.[1]

5. Shuffle the remaining cards face down and place them in the middle of the table as a supply.[1]

6. Deal 16 cards face down from the supply in a stack, place the 'last round' card on top of this stack, and place the rest of the card supply on top of this.[1]

7. Players choose a starting player using any preferred method.[1]

8. On a player's turn, he must take one of two actions:

A. Draw and place a card: The player draws the top-most card from the supply and places it face up next to any row card, up to a maximum of 3 cards next to a row card.[1]

B. Take a card row: A player may only take a row card if it has at least one card next to it.[2] The player takes the row card and all cards next to it and places them face up in his play area.[2] If the player takes a golden Joker, he must reveal the top-most card from the supply and place it face up in his play area.[2] The player then sorts the cards by color, setting any jokers aside to decide their color at the end of the game.[2]

9. After a player takes a card row, he takes no more turns in that round.[2] The player's left neighbor then takes a turn.[1]

10. If all players but one have passed, that player may continue to draw and place as many cards as he can before choosing to take a card row and finishing the round.[2]

11. When each player has taken a card row, the round ends.[1]

12. To begin a new round, place the row cards back in the middle of the table and start with the player who took the last card row in the previous round.[2]

13. The game enters the last round when the 'last round' card is drawn.[2]

14. At the end of the game, players decide which color their jokers are.[2]

15. Each player counts the cards in each color.[2]

16. Each player chooses which 3 of his colors score plus points; all other colors score minus points.[2]

17. The player with the most points wins.[3][2]

[1] RULEBOOK Coloretto — Rulebook · p.2 · PREPARATION · PLAYING THE GAME · A. Draw and place a card

[2] RULEBOOK Coloretto — Rulebook · p.2 · B. Take a card row · End of a round · GAME END · Scoring

[3] RULEBOOK Coloretto — Rulebook · p.1 · FOR TWO PLAYERS · OVERVIEW · CONTENTS

So says the rulebook. So plays the table.

🔧 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 209 ms · ask 3808 ms · total 4019 ms
single-flight (PR-5): queued 0 ms · generation 4019 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 2, "score": 0.04918, "snippet": "Each player takes one summary card. The players choose whether to play with the scoring table on the brown side or on the violet side of the summary card. Note: we recommend beginning with the brown side. With 3 to 5 players, play with the brown row cards. Place one row card in the middle of the tab", "headingPath": "PREPARATION · PLAYING THE GAME · A. Draw and place a card", "sharpsignalDocId": 650}, {"page": 2, "score": 0.048387, "snippet": "The player takes any of the row cards and all the cards next to it and places them face up in his play area. The player then sorts the cards by color. If a player has taken a joker, he sets it aside for now. He must decide which color to place it with at the end of the game, but not sooner. If a pla", "headingPath": "B. Take a card row · End of a round · GAME END · Scoring", "sharpsignalDocId": 650}, {"page": 1, "score": 0.047619, "snippet": "Example (brown side): Andy has 1 Joker, 1 '+2' card, 6 green cards, 4 yellow cards, 3 red cards, and 2 blue cards. As he already scores the most he can for his 6 green cards, he places his joker with his yellow cards. +6 points +21 points +15 points With 2 players, the following changes to the rules", "headingPath": "FOR TWO PLAYERS · OVERVIEW · CONTENTS", "sharpsignalDocId": 650}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "PREPARATION · PLAYING THE GAME · A. Draw and place a card", "sharpsignalDocId": 650}, {"page": 2, "quote": null, "headingPath": "B. Take a card row · End of a round · GAME END · Scoring", "sharpsignalDocId": 650}, {"page": 1, "quote": null, "headingPath": "FOR TWO PLAYERS · OVERVIEW · CONTENTS", "sharpsignalDocId": 650}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 650 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 650 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 0.90814 of 1818 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 25, 2026 09:28 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 Coloretto — Rulebook (corpus doc 650)	PREPARATION · PLAYING THE GAME · A. Draw and place a card	p.2	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Coloretto — Rulebook (corpus doc 650)	B. Take a card row · End of a round · GAME END · Scoring	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 Coloretto — Rulebook (corpus doc 650)	FOR TWO PLAYERS · OVERVIEW · CONTENTS	p.1	0.047619 (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 3 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 Coloretto — Rulebook (corpus doc 650)	PREPARATION · PLAYING THE GAME · A. Draw and place a card	p.2	#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 Coloretto — Rulebook (corpus doc 650)	FOR TWO PLAYERS · OVERVIEW · CONTENTS	p.1	#3	0.047619 (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 Coloretto — Rulebook (corpus doc 650)	B. Take a card row · End of a round · GAME END · Scoring	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 Coloretto — Rulebook (corpus doc 650)	PREPARATION · PLAYING THE GAME · A. Draw and place a card	p.2	no quote on the wire
[2]	RULEBOOK Coloretto — Rulebook (corpus doc 650)	B. Take a card row · End of a round · GAME END · Scoring	p.2	no quote on the wire
[3]	RULEBOOK Coloretto — Rulebook (corpus doc 650)	FOR TWO PLAYERS · OVERVIEW · CONTENTS	p.1	no quote on the wire

generation — timing and the path taken

timing split: retrieval 209 ms · first delta 1010 ms · total 4019 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 209 ms · ask 3808 ms · gateway work 4019 ms · total 4019 ms
tokens in (the prompt the answerer read): 1763
tokens out (what the answerer generated): 601
tok/sec: 202.8 tok/sec — 601 output tokens in 2.964 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 47s 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 3s 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 583), 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.