You asked
How do I set up the game?
Answered counted as answeredAsked with: Love Letterbg-277085-en-1e
1. Give each player a reference card and return any remaining reference cards to the bag [1]. 2. Shuffle the 21 character cards to create the deck [1]. (Note: For the classic version, before setup, return 1 Guard, 2 Chancellors, and 2 Spies to the bag [2]). 3. Place the deck facedown on the table within easy reach of all players along with the 13 favor tokens [1]. 4. Take the top card of the deck and set it aside facedown without looking at it [1]. 5. If you are playing a two-player game, take three more cards and set those aside faceup [1]. 6. Deal each player one card from the deck as their starting hand [1].
🔧 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 262 ms · ask 3141 ms · total 2159387 ms
- single-flight (PR-5)
- queued 2155974 ms · generation 3413 ms
- retrieval refs (raw)
- [{"page": 7, "score": 0.04866, "snippet": "To start a new round, repeat steps 2-4 of setup (shuffle the character cards, set some aside, and deal each player one card). The player who won the previous round takes the first turn. If there was a tie in the previous round, randomly decide among the tied players who takes the first turn. The gam", "headingPath": "Starting the Next Round · Winning the Game", "sharpsignalDocId": 120}, {"page": 3, "score": 0.048652, "snippet": "Give each player a reference card and return any remaining reference cards to the bag. Reference cards list the values, effects, and quantity of each character card type. Shuffle the 21 character cards to create the deck. Place the deck facedown on the table within easy reach of all players along wi", "headingPath": "Setup", "sharpsignalDocId": 120}, {"page": 14, "score": 0.04598, "snippet": "4 Included in this edition of Love Letter are the rules to play the classic version of the game, though it supports only 2-4 players . To play the classic version, before setup, return these cards to the bag: ❧ 1 Guard ❧ 2 Chancellors ❧ 2 Spies All other rules for the game are unchanged. 1", "headingPath": "Rule Mistakes · . Classic Version", "sharpsignalDocId": 120}, {"page": 16, "score": 0.031746, "snippet": "Shuffle the 21 cards. Set one aside facedown (and three more faceup if playing with two players). Deal one card to each player. The player who last hand-wrote a letter (or won the previous round) takes the first turn. Draw one card. Play one of your two cards, resolving its effect. The round ends in", "headingPath": "Setup & Start of Round · Taking A Turn · End of Round", "sharpsignalDocId": 120}, {"page": 12, "score": 0.03125, "snippet": "Choose another player. You and that player secretly compare your hands. Whoever has the lowervalue card is out of the round. If there is a tie, neither player is out of the round. Choose another player and secretly look at their hand (without revealing it to anyone else). Choose another player and n", "headingPath": "3 . Baron · 2 . Priest · 1 . Guard", "sharpsignalDocId": 120}, {"page": 10, "score": 0.030769, "snippet": "Draw two cards from the deck into your hand. Choose and keep one of the three cards now in your hand, and secretly place the other two facedown on the bottom of the deck in any order (without revealing them to anyone else). If there is only one card in the deck, draw it and return one card. If there", "headingPath": "6 . Chancellor · 5 . Prince", "sharpsignalDocId": 120}, {"page": 4, "score": 0.030303, "snippet": "Love Letter is played over several game rounds in which you enlist the allies, friends, and family of the Princess to carry a letter of intent to her. The card in your hand represents the person who currently carries your letter, but this can change during the round as you draw and play cards. To wi", "headingPath": "Playing the Game · Player Turn", "sharpsignalDocId": 120}, {"page": 11, "score": 0.029412, "snippet": "Until the start of your next turn , other players cannot choose you for their card effects. In the rare case that all other players still in the round are 'protected' by a Handmaid when you play a card, do the following: ❧ If that card requires you to choose another player (Guard, Priest, Baron, Kin", "headingPath": "4 . Handmaid", "sharpsignalDocId": 120}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 120}, {"page": 14, "quote": null, "headingPath": "Rule Mistakes · . Classic Version", "sharpsignalDocId": 120}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 120 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 120 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 6, 2026 14:47
retrieval — what the search arm returned
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 Love Letter — Rulebook (corpus doc 120) | Starting the Next Round · Winning the Game | p.7 | 0.04866 (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 Love Letter — Rulebook (corpus doc 120) | Setup | p.3 | 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 |
| #3 | RULEBOOK Love Letter — Rulebook (corpus doc 120) | Rule Mistakes · . Classic Version | p.14 | 0.04598 (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)) | 290 |
| #4 | RULEBOOK Love Letter — Rulebook (corpus doc 120) | Setup & Start of Round · Taking A Turn · End of Round | p.16 | 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 |
| #5 | RULEBOOK Love Letter — Rulebook (corpus doc 120) | 3 . Baron · 2 . Priest · 1 . Guard | p.12 | 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 |
| #6 | RULEBOOK Love Letter — Rulebook (corpus doc 120) | 6 . Chancellor · 5 . Prince | p.10 | 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 |
| #7 | RULEBOOK Love Letter — Rulebook (corpus doc 120) | Playing the Game · Player Turn | 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 Love Letter — Rulebook (corpus doc 120) | 4 . Handmaid | p.11 | 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 |
chosen chunks — what the answer actually cited
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.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Love Letter — Rulebook (corpus doc 120) | Setup | p.3 | no quote on the wire |
| [2] | RULEBOOK Love Letter — Rulebook (corpus doc 120) | Rule Mistakes · . Classic Version | p.14 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 262 ms · first delta 2160 ms · total 2159387 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 2155974 ms · retrieval 262 ms · ask 3141 ms · gateway work 3413 ms · total 2159387 ms
- tokens in (the prompt the answerer read)
- 1387
- tokens out (what the answerer generated)
- 166
- tok/sec
- 137.3 tok/sec — 166 output tokens in 1.209 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 44s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 42), 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.