Ruling — Diamant

You asked

How do I play?

Answered counted as answered

Asked with: Diamantbg-15512-en-1e

1. At the start of each round, the Guide reveals the Artifact card under the corresponding Temple display card, showing it to all players before adding it to the Quest deck and shuffling it.[1]

2. The Guide reveals the top card of the Quest deck and places it at the end of the Temple row.[1]

3. Players encounter one of three room types:

- Treasure cards (blue borders): The Guide takes the specified value of gems from the supply and splits it equally among all players currently exploring the ruins, leaving any remainder on the card.[1] Players keep these gems in FRONT of their tents; they are only safe if the player exits the temple before a Hazard forces them out.[1]

- Artifact cards (yellow borders): These stay on the table and can only be claimed by an explorer leaving the temple alone.[1]

- Hazard cards (red borders): If the card matches a previous Hazard revealed in the temple this round, disaster strikes, all explorers in the temple must flee and return all gems gathered this round to the supply, and the round ends.[1] If it does not match a previous Hazard, the card is kept in the Temple row.[1]

4. After a room is resolved, if the round is not over, players simultaneously and secretly select an Explore or Exit card and place it face-down.[2]

5. The Guide signals everyone to reveal their cards at the same time.[2]

6. If all players decide to stay exploring, the Guide starts a new turn by revealing a new room.[2]

7. If multiple players decide to exit, they split the total of leftover gems from previous Temple rooms if possible (leaving leftovers on the cards), and those players place their gathered gems from the round safely behind their tents.[2] Players who exit cannot return until the next round.[2]

8. If only one player decides to leave, they receive all leftover gems from previous Temple rooms and claim any revealed Artifact cards in the Temple row.[2] They also store their gathered gems behind their tent.[2]

9. If all players have left the temple, the round ends.[2]

10. At the end of a round (whether ended by a Hazard or all players leaving):

- If ended by a Hazard, the second matching Hazard card is removed from the Quest deck for the rest of the game.[3]

- All remaining Treasure and Hazard cards in the Temple row are collected and shuffled back into the Quest deck.[3]

- Any leftover gems on Room cards are returned to the supply.[3]

- Any unclaimed Artifact cards are removed from the game.[3]

- Players ensure gems are either returned to the supply (if stopped by a Hazard) or stored behind their tents.[3]

11. The Guide begins the next round by revealing the next Artifact and shuffling it into the Quest deck.[3]

12. The game continues for 5 rounds.[3]

13. After the 5th round, the game ends and final scores are tallied.[3]

14. Players count the total Treasure value of gems stored safely in their tents and add the Treasure values of any claimed Artifact cards.[3]

15. The player with the highest total value wins; in a tie, the player with the most Artifacts wins, otherwise players share the victory.[3]

[1] RULEBOOK Diamant — Rulebook · p.2 · Game Play · 1) Revealing a New Room

[2] RULEBOOK Diamant — Rulebook · p.3 · 1) Revealing a New Room · 2) Should I stay or Should I go?

[3] RULEBOOK Diamant — Rulebook · p.4 · 3) End of a Round · End of the Game

The sage rests. The game continues.

🔧 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 81 ms · ask 4332 ms · total 12238 ms
single-flight (PR-5): queued 7823 ms · generation 4415 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 4, "score": 0.04918, "snippet": "The game round ends when either two matching Hazards have been revealed, forcing the explorers out, or after all players have left the temple. If the round has ended due to a Hazard, remove the second matching Hazard card in the Temple row from the Quest deck for the rest of the game. There are only", "headingPath": "3) End of a Round · End of the Game", "sharpsignalDocId": 718}, {"page": 2, "score": 0.047875, "snippet": "At the start of each round, the Guide player reveals the Artifact card under the corresponding card of the Temple display, showing it to all players before adding to the Quest deck and shuffling it. In each of the 5 rounds, players explore the temple one room at a time, going deeper and deeper until", "headingPath": "Game Play · 1) Revealing a New Room", "sharpsignalDocId": 718}, {"page": 3, "score": 0.032258, "snippet": "In the above example, if the next card revealed has Spiders, Bats, or a Snake, all players still exploring will lose their collected treasures from that round. After the new room is resolved, if the round is not over, players must now decide whether to continue to EXPLORE or EXIT with the treasure t", "headingPath": "1) Revealing a New Room · 2) Should I stay or Should I go?", "sharpsignalDocId": 718}, {"page": 1, "score": 0.03125, "snippet": "Players: 3 - 8 · Ages: 8 and up · Duration: 20 - 40 minutes A local university in Peru has reported that the excavation site of an Incan temple is about to collapse and hired an expedition to venture into the ruins to recover artifacts rumored to be in the temple before they are lost forever. Player", "headingPath": "Designed by Alan R. Moon & Bruno Faidutti · Components · 8 Folded Tents 110 Treasures (Gems) · Setup", "sharpsignalDocId": 718}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "Game Play · 1) Revealing a New Room", "sharpsignalDocId": 718}, {"page": 3, "quote": null, "headingPath": "1) Revealing a New Room · 2) Should I stay or Should I go?", "sharpsignalDocId": 718}, {"page": 4, "quote": null, "headingPath": "3) End of a Round · End of the Game", "sharpsignalDocId": 718}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 718 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 718 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 0.92707 of 2523 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 26, 2026 10:58 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 Diamant — Rulebook (corpus doc 718)	3) End of a Round · End of the Game	p.4	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Diamant — Rulebook (corpus doc 718)	Game Play · 1) Revealing a New Room	p.2	0.047875 (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 Diamant — Rulebook (corpus doc 718)	1) Revealing a New Room · 2) Should I stay or Should I go?	p.3	0.032258 (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 Diamant — Rulebook (corpus doc 718)	Designed by Alan R. Moon & Bruno Faidutti · Components · 8 Folded Tents 110 Treasures (Gems) · Setup	p.1	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

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 4 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 Diamant — Rulebook (corpus doc 718)	Game Play · 1) Revealing a New Room	p.2	#2	0.047875 (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 Diamant — Rulebook (corpus doc 718)	3) End of a Round · End of the Game	p.4	#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
#3	RULEBOOK Diamant — Rulebook (corpus doc 718)	Designed by Alan R. Moon & Bruno Faidutti · Components · 8 Folded Tents 110 Treasures (Gems) · Setup	p.1	#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
#4	RULEBOOK Diamant — Rulebook (corpus doc 718)	1) Revealing a New Room · 2) Should I stay or Should I go?	p.3	#3	0.032258 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Diamant — Rulebook (corpus doc 718)	Game Play · 1) Revealing a New Room	p.2	no quote on the wire
[2]	RULEBOOK Diamant — Rulebook (corpus doc 718)	1) Revealing a New Room · 2) Should I stay or Should I go?	p.3	no quote on the wire
[3]	RULEBOOK Diamant — Rulebook (corpus doc 718)	3) End of a Round · End of the Game	p.4	no quote on the wire

generation — timing and the path taken

timing split: retrieval 81 ms · first delta 894 ms · total 12238 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 7823 ms · retrieval 81 ms · ask 4332 ms · gateway work 4415 ms · total 12238 ms
tokens in (the prompt the answerer read): 2122
tokens out (what the answerer generated): 706
tok/sec: 202.9 tok/sec — 706 output tokens in 3.479 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 45s 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 2s 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 652), 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.