Ruling — Gloomhaven: Jaws of the Lion

You asked

How do I play?

Abstained — no grounded answer; closest passages below counted as honest abstain

Asked with: Gloomhaven: Jaws of the Lionbg-291457-en-1e

I looked through Gloomhaven: Jaws of the Lion's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.

The closest rulebook passages are below — check them before ruling.

RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook · p.6 · Playing the Game

Now that the game has been set up properly, we can start playing! Gameplay within a scenario is broken up into a series of rounds. In each round, all players will select which ability cards they would like to play. The chosen cards will determine the "initiative order", which is the sequence in whic

RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook · p.1 · Learn to Play Guide

W eleome to Gloomhaven! This game is fully cooperative, with players working together to navigate their way through a campaign of scenarios. You will not play it all in one sitting, but it can easily be saved at the end of any single scenario. This book is meant to walk you step-by-step through the

RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook · p.3 · Playing by Yourself?

If you are playing the game by yourself, you will need to control two separate characters. Take note that this is a more complex experience. If there are two to four players, it is highly recommended that each player only controls a single character. To choose which character to play, find the large

RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook · p.3 · Scenario 1 Rules

To start, perhaps you noticed this in the Scenario Book: This means to take that first sticker from the sticker sheet, labeled "Roadside Ambush", and place it in the "B1" square of the city map board, such that the artwork lines up. These stickers are permanent. If you would prefer not to make perma

RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook · p.4 · Play Area Setup

Using these character materials and other components, we will now set up Scenario 1. Each player should place their character mat ①, player reference , six level "A" ability cards 3 , attack modifier deck (the deck of smaller cards) , and hit point dial in front of them. The red side of the dial sho

Strategy guides → — community tips, kept separate from rulings

🔧 debug — where this ruling came from

outcome

ABSTAINED — Abstained — no grounded answer; closest passages below

warm abstain

this ruling — W1 — generic warm abstain · receipt: none (generic)

corpus profile

live,vps

answerer pin (deploy-frozen, attribution only)

gemma4:26b think:false 5571076f3d70

timings

search 76 ms · ask 2948 ms · total 5137 ms

single-flight (PR-5)

queued 2111 ms · generation 3026 ms

retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read

[{"page": 6, "score": 0.048172, "snippet": "Now that the game has been set up properly, we can start playing! Gameplay within a scenario is broken up into a series of rounds. In each round, all players will select which ability cards they would like to play. The chosen cards will determine the \"initiative order\", which is the sequence in whic", "headingPath": "Playing the Game", "sharpsignalDocId": 61}, {"page": 1, "score": 0.048139, "snippet": "W eleome to Gloomhaven! This game is fully cooperative, with players working together to navigate their way through a campaign of scenarios. You will not play it all in one sitting, but it can easily be saved at the end of any single scenario. This book is meant to walk you step-by-step through the ", "headingPath": "Learn to Play Guide", "sharpsignalDocId": 61}, {"page": 3, "score": 0.047883, "snippet": "If you are playing the game by yourself, you will need to control two separate characters. Take note that this is a more complex experience. If there are two to four players, it is highly recommended that each player only controls a single character. To choose which character to play, find the large", "headingPath": "Playing by Yourself?", "sharpsignalDocId": 61}, {"page": 3, "score": 0.045743, "snippet": "To start, perhaps you noticed this in the Scenario Book: This means to take that first sticker from the sticker sheet, labeled \"Roadside Ambush\", and place it in the \"B1\" square of the city map board, such that the artwork lines up. These stickers are permanent. If you would prefer not to make perma", "headingPath": "Scenario 1 Rules", "sharpsignalDocId": 61}, {"page": 4, "score": 0.044854, "snippet": "Using these character materials and other components, we will now set up Scenario 1. Each player should place their character mat ①, player reference , six level \"A\" ability cards 3 , attack modifier deck (the deck of smaller cards) , and hit point dial in front of them. The red side of the dial sho", "headingPath": "Play Area Setup", "sharpsignalDocId": 61}, {"page": 30, "score": 0.041931, "snippet": "There are a few other rules we weren't able to introduce yet that you will need as you go deeper into the campaign. These are outlined below, but also note that the Rules Glossary contains a comprehensive detailing of all the rules in the game. If you ever have a question about anything, you will fi", "headingPath": "Final Rules", "sharpsignalDocId": 61}, {"page": 6, "score": 0.041899, "snippet": "Each player will now privately and simultaneously select two ability cards from their hand of six cards to play face down in front of them. During this step, players can make general statements about their actions for the round and discuss strategy, but they cannot show other players their cards nor", "headingPath": "Card Selection", "sharpsignalDocId": 61}, {"page": 25, "score": 0.029412, "snippet": "Now, retrieve the element board from the game box and place the six element tokens from the tray on the \"Inert\" column. This board will be discussed further on the following page.", "headingPath": "Element Board", "sharpsignalDocId": 61}]

citations (raw) — what the answer cited, chosen from a retrieval this page cannot show

[]

boost provenance — errata + base rulebook (E2/E3)

no registered errata card matched this query; base rulebook doc 61 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 61 boosted

answered-before recall

no past answered ruling for this game matched closely enough

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 14, 2026 14:31

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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Playing the Game	p.6	0.048172 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Learn to Play Guide	p.1	0.048139 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Playing by Yourself?	p.3	0.047883 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Scenario 1 Rules	p.3	0.045743 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Play Area Setup	p.4	0.044854 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Final Rules	p.30	0.041931 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Card Selection	p.6	0.041899 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Element Board	p.25	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))	179

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 80 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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Playing by Yourself?	p.3	#3	0.047883 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	End of Round	p.12	#18	0.024892 (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
#3	RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Running Out of Cards	p.12	#10	0.028259 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	City Interaction: Items	p.19	#15	0.025098 (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
#5	RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Short Rest	p.12	#11	0.027497 (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
#6	RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Learn to Play Guide	p.1	#2	0.048139 (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
#7	RULEBOOK Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Scenario 1 Rules	p.3	#4	0.045743 (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 Gloomhaven: Jaws of the Lion — Rulebook (corpus doc 61)	Playing the Game	p.6	#1	0.048172 (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

generation — timing and the path taken

timing split: retrieval 76 ms · first delta 2945 ms · total 5137 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 2111 ms · retrieval 76 ms · ask 2948 ms · gateway work 3026 ms · total 5137 ms
tokens in (the prompt the answerer read): 2247
tokens out (what the answerer generated): 9
tok/sec: 204.5 tok/sec — 9 output tokens in 0.044 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 46s 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: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped

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 9), 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.