RuleSage cited table rulings
← Mandala

You asked

What needs to be placed on the table before the first round begins?

Answered counted as answered

Asked with: Mandalabg-264241-en-1e

To set up the game before the first round begins, follow these steps: 1. Place the play mat in the middle of the play area, between the two players [1]. 2. Shuffle the sand cards thoroughly and place them face down beside the play mat as the draw deck [1]. 3. Leave space beside the draw deck for a face-up discard pile [1]. 4. For each of the two Mandalas on the play mat, draw 2 cards from the deck and place them face up in the Mountain [1]. 5. Place an action overview card in front of each player [1]. 6. Draw 6 cards from the deck and put them into your hand [1]. 7. Draw 2 cards from the deck and place them face down in your Cup [1].

[1] RULEBOOK Mandala — Rulebook · p.2 · Setup
🔧 debug — where this ruling came from
outcome
ANSWERED — Answered
corpus profile
live
answerer pin (deploy-frozen, attribution only)
gemma4:26b think:false 5571076f3d70
timings
search 242 ms · ask 3665 ms · total 40759 ms
single-flight (PR-5)
queued 36842 ms · generation 3917 ms
retrieval refs (raw)
[{"page": 3, "score": 0.032787, "snippet": "Beginning with the first player, you alternate taking turns until the end of the game. On your turn, you must take one of the following three actions, which will be explained in detail on the following pages: or Play cards of one color into one of your Fields. Do not draw any cards this turn. Check ", "headingPath": "Course of Play · B - GROW FIELD & NO DRAW · C - DISCARD & REDRAW · The Rule of Color", "sharpsignalDocId": 530}, {"page": 5, "score": 0.032258, "snippet": "As soon as cards of all 6 colors have been played into a Mandala (consider the cards in its Mountain and its two Fields) , the Mandala is complete and must be destroyed at the end of that turn; this may cause the game to end (see next page) . Starting with the player who played the most cards in the", "headingPath": "Completing a Mandala · DESTROYING A MANDALA · a) If you claim cards of a new color, not present in your River:", "sharpsignalDocId": 530}, {"page": 2, "score": 0.031746, "snippet": "Place the play mat in the middle of the play area, between the two of you. Shuffle the sand cards very thoroughly and place them face down beside the play mat as the draw deck . Leave space beside it for a face-up discard pile . For each of the two Mandalas on the play mat, draw 2 cards from the dec", "headingPath": "Setup", "sharpsignalDocId": 530}, {"page": 5, "score": 0.03125, "snippet": "If one player has no cards in their Field when a Mandala completes, both players still take turns to choose colors in the Mountain as usual, but the player with no cards in their Field must place all of the cards they claim in the discard pile. They do not add any of these cards to their River or Cu", "headingPath": "No cards in a Field", "sharpsignalDocId": 530}, {"page": 4, "score": 0.030769, "snippet": "Cards in the Mountain will be claimed when a Mandala is completed, and added to your Rivers and Cups to earn points at the end of the game. When you choose this action, do the following in this order: Choose exactly 1 card from your hand and place it face up in one of the two Mountains. You must res", "headingPath": "A - BUILD MOUNTAIN & DRAW · B - GROW FIELD & NO DRAW", "sharpsignalDocId": 530}, {"page": 4, "score": 0.030303, "snippet": "If you cannot or do not want to play cards, you can instead discard cards from your hand and replace them with cards from the draw deck. When you choose this action, do the following in this order: Choose 1 or more cards of one color from your hand and place them face up in the discard pile. (The Ru", "headingPath": "C - DISCARD & REDRAW", "sharpsignalDocId": 530}, {"page": 6, "score": 0.029851, "snippet": "The end of the game is triggered when the draw deck is exhausted or one of you adds a 6th card to their River. If the draw deck is exhausted, reshuffle the discard pile to create a new draw deck. Then continue playing until the next time a Mandala is completed. The game ends immediately after that M", "headingPath": "End of the game · Exhausting the Deck · Adding a 6th Card to a River · Scoring · ANNA'S RIVER", "sharpsignalDocId": 530}, {"page": 1, "score": 0.029412, "snippet": "A tactical card game for 2 players aged 10 and up, playing time: 30 minutes The Mandala: the symbol of an ancient and sacred ritual. Colored sand is laid to create a symbolic map of the world, before the pattern is ceremonially destroyed and the sand cast into the river-an ever repeating cycle of li", "headingPath": "Object of the Game · Components · 110 playing cards:", "sharpsignalDocId": 530}]
citations (raw)
[{"page": 2, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 530}]
boost provenance — errata + base rulebook (E2/E3)
no registered errata card matched this query; base rulebook doc 530 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 530 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)
debug row retained until
Nov 7, 2026 08:02

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 rankdocumentheadingpage fused RRF scoresnippet chars
#1 RULEBOOK Mandala — Rulebook (corpus doc 530) Course of Play · B - GROW FIELD & NO DRAW · C - DISCARD & REDRAW · The Rule of Color p.3 0.032787 (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 Mandala — Rulebook (corpus doc 530) Completing a Mandala · DESTROYING A MANDALA · a) If you claim cards of a new color, not present in your River: p.5 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
#3 RULEBOOK Mandala — Rulebook (corpus doc 530) Setup p.2 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
#4 RULEBOOK Mandala — Rulebook (corpus doc 530) No cards in a Field p.5 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 Mandala — Rulebook (corpus doc 530) A - BUILD MOUNTAIN & DRAW · B - GROW FIELD & NO DRAW p.4 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 Mandala — Rulebook (corpus doc 530) C - DISCARD & REDRAW 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
#7 RULEBOOK Mandala — Rulebook (corpus doc 530) End of the game · Exhausting the Deck · Adding a 6th Card to a River · Scoring · ANNA'S RIVER p.6 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 Mandala — Rulebook (corpus doc 530) Object of the Game · Components · 110 playing cards: p.1 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

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.

#documentheadingpagequote chars
[1] RULEBOOK Mandala — Rulebook (corpus doc 530) Setup p.2 no quote on the wire
timing split
retrieval 242 ms · first delta 2740 ms · total 40759 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown
queued 36842 ms · retrieval 242 ms · ask 3665 ms · gateway work 3917 ms · total 40759 ms
tokens in (the prompt the answerer read)
2785
tokens out (what the answerer generated)
170
tok/sec
148.6 tok/sec — 170 output tokens in 1.144 s of generation
live seat (read from the running child)
answering — gemma4:26b think:false · num_ctx 32768 (live-verified 49s 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.
outcome
ANSWERED — Answered
abstain rationale (n/a — this ruling answered)
answered — no abstain rationale applies
decision
NOT_SETUP_SHAPED — no setup-shape pattern matched this question

this game registers NO errata cards (edition 461), 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.