Ruling — Lovecraft Letter

You asked

How do I play?

Answered counted as answered

Asked with: Lovecraft Letterbg-198740-en-1e

Lovecraft Letter is played in a series of rounds.[1]

**A Turn**

1. At the start of each of their future turns (before adding a new card to their hand), an Insane player must make a Sanity Check by revealing as many cards from the top of the deck as the player has Insanity cards in their discard pile, one at a time.[2]

2. If an Insane player reveals an Insanity card during this check, they are immediately knocked out of the round.[2]

3. If the Sanity Check is passed, all revealed cards are discarded without applying their effect.[2]

4. On your turn, draw the top card from the deck and add it to your hand.[1]

5. Choose one of the two cards now in your hand and discard it face up in front of you.[1]

6. Apply any effect on the card you discarded, even if it is bad for you.[1]

7. Once the card's effect is applied and the card is in your discard pile, the turn passes to the player to your left.[1]

**End of a Round**

1. A round ends if the deck is empty at the end of a player's turn,[3] or if a Sanity Check cannot be performed because the deck is empty,[2] or if all players but one have been knocked out of the round.[3]

2. All players still in the round reveal their hands.[3]

3. If multiple players have the same number in their hand, they are knocked out of the round.[3]

4. The player with the highest number in their hand wins the round.[3]

5. After the end of the round, check the winner's state of mind: a player is Insane if an Insanity card is ever in their discard pile, otherwise they are Sane.[3]

6. Give the winner a Sanity token and have them place it with the face corresponding to their state of mind up.[3]

7. A new round begins with the winner of the previous round as the starting player.[3]

**Winning the Game**

A player wins the game after any of the following conditions are met:

1. They have 2 Sanity tokens face up.[3]

2. They have 3 Sanity tokens face up.[3]

3. They have won the previous round thanks to the Insane effect of Cthulhu.[3]

[1] RULEBOOK Lovecraft Letter — Rulebook · p.6 · Setup · Taking a Turn · Discarding

[2] RULEBOOK Lovecraft Letter — Rulebook · p.7 · Discarding · Hand · Insanity · Out of the Round

[3] RULEBOOK Lovecraft Letter — Rulebook · p.8 · End of a Round · Game End · Honesty

That's the page. Back to 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 102 ms · ask 4334 ms · total 5083 ms
single-flight (PR-5): queued 646 ms · generation 4437 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 2, "score": 0.04866, "snippet": "2 A Game by Seiji Kanai For 2 To 6 Players, Ages 14 And Up Contents Goal .................................................................................3 How to Win .......................................................................3 Components .................................................", "headingPath": "", "sharpsignalDocId": 838}, {"page": 5, "score": 0.047379, "snippet": "Card Count : This is the number of copies of the card in the game. It is also used to indicate whether a card can be used for its Sane effect, or for its Insane effect, when possible (see Insanity , page 7). Art : A visual depiction of the card Card Effect : What the card does. Insanity cards have b", "headingPath": "Game Cards · Reference Cards · Sanity Tokens · Setup", "sharpsignalDocId": 838}, {"page": 8, "score": 0.047131, "snippet": "A round ends if the deck is empty at the end of a player's turn. All players still in the round reveal their hands. If multiple players have the same number in their hand, they are knocked out of the round. The player with the highest number in their hand wins the round. A round also ends if all pla", "headingPath": "End of a Round · Game End · Honesty", "sharpsignalDocId": 838}, {"page": 3, "score": 0.046244, "snippet": "In Lovecraft Letter , you are a person who has arrived in Egypt to help your cousin, only to discover they are missing. You follow a series of clues apparently left behind for you to find, but beware, as some of them contain forbidden secrets or are protected by supernatural beings that could threat", "headingPath": "Goal · How to Win", "sharpsignalDocId": 838}, {"page": 6, "score": 0.045695, "snippet": "Lovecraft Letter is played in a series of rounds. At the end of each round, a winner is determined thanks to the clue they are holding in their hand (its number), as well as their state of mind (Sane or Insane) (see End of a Round , page 8). Win a certain number of rounds in a certain state of mind ", "headingPath": "Setup · Taking a Turn · Discarding", "sharpsignalDocId": 838}, {"page": 13, "score": 0.032258, "snippet": "Same effect as Professor Henry Armitage. When you discard Mi-Go during your turn, choose another player. You add their hand in yours (you have 2 cards in your hand now). They must take Mi-Go Braincase in their hand (they now have one card). Since you have 2 cards in hand, you discard a card. If all ", "headingPath": "Mi-Go · Randolph Carter · Nyarlathotep", "sharpsignalDocId": 838}, {"page": 2, "score": 0.030303, "snippet": "In the 1920s, the world is still in the chaos of the First World War. In the middle of all this, one of your relatives has encountered something mysterious in Egypt. Strange shadows that come to life … Letters with undecipherable texts and strange symbols… Upon arriving you find out he is missing an", "headingPath": "A Game by Seiji Kanai For 2 To 6 Players, Ages 14 And Up · Contents", "sharpsignalDocId": 838}, {"page": 7, "score": 0.029911, "snippet": "If you discard a card with an effect that requires you to choose a player that cannot be chosen due to another card effect (Elder Sign, Liber Ivonis), your card is discarded without effect. Several effects in the game refer to the 'hand' of a player. It is a shortcut for 'the card in the hand' of a ", "headingPath": "Discarding · Hand · Insanity · Out of the Round", "sharpsignalDocId": 838}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 6, "quote": null, "headingPath": "Setup · Taking a Turn · Discarding", "sharpsignalDocId": 838}, {"page": 7, "quote": null, "headingPath": "Discarding · Hand · Insanity · Out of the Round", "sharpsignalDocId": 838}, {"page": 8, "quote": null, "headingPath": "End of a Round · Game End · Honesty", "sharpsignalDocId": 838}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 838 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 838 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 0.90915 of 1596 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 24, 2026 07:24 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 Lovecraft Letter — Rulebook (corpus doc 838)		p.2	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 Lovecraft Letter — Rulebook (corpus doc 838)	Game Cards · Reference Cards · Sanity Tokens · Setup	p.5	0.047379 (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 Lovecraft Letter — Rulebook (corpus doc 838)	End of a Round · Game End · Honesty	p.8	0.047131 (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 Lovecraft Letter — Rulebook (corpus doc 838)	Goal · How to Win	p.3	0.046244 (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 Lovecraft Letter — Rulebook (corpus doc 838)	Setup · Taking a Turn · Discarding	p.6	0.045695 (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 Lovecraft Letter — Rulebook (corpus doc 838)	Mi-Go · Randolph Carter · Nyarlathotep	p.13	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
#7	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	A Game by Seiji Kanai For 2 To 6 Players, Ages 14 And Up · Contents	p.2	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 Lovecraft Letter — Rulebook (corpus doc 838)	Discarding · Hand · Insanity · Out of the Round	p.7	0.029911 (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 19 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 Lovecraft Letter — Rulebook (corpus doc 838)	Setup · Taking a Turn · Discarding	p.6	#5	0.045695 (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 Lovecraft Letter — Rulebook (corpus doc 838)	End of a Round · Game End · Honesty	p.8	#3	0.047131 (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 Lovecraft Letter — Rulebook (corpus doc 838)	Discarding · Hand · Insanity · Out of the Round	p.7	#8	0.029911 (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 re-ranker chose it
#4	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	Cthulhu Mythos · Investigators · Deep Ones	p.9	#16	0.013158 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one))	vector	the re-ranker chose it
#5	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	A Game by Seiji Kanai For 2 To 6 Players, Ages 14 And Up · Contents	p.2	#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
#6	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	Mi-Go · Randolph Carter · Nyarlathotep	p.13	#6	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
#7	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	Goal · How to Win	p.3	#4	0.046244 (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
#8	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)		p.2	#1	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))	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 Lovecraft Letter — Rulebook (corpus doc 838)	Setup · Taking a Turn · Discarding	p.6	no quote on the wire
[2]	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	Discarding · Hand · Insanity · Out of the Round	p.7	no quote on the wire
[3]	RULEBOOK Lovecraft Letter — Rulebook (corpus doc 838)	End of a Round · Game End · Honesty	p.8	no quote on the wire

generation — timing and the path taken

timing split: retrieval 102 ms · first delta 1820 ms · total 5083 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 646 ms · retrieval 102 ms · ask 4334 ms · gateway work 4437 ms · total 5083 ms
tokens in (the prompt the answerer read): 2648
tokens out (what the answerer generated): 521
tok/sec: 203.4 tok/sec — 521 output tokens in 2.561 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s 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 0s 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 773), 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.