You asked
How do I play?
Answered counted as answeredAsked with: Edge of Darknessbg-229491-en-1e
Rule found, game on.
🔧 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 108 ms · ask 7336 ms · total 11345 ms
- single-flight (PR-5)
- queued 3898 ms · generation 7447 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 10, "score": 0.04918, "snippet": "Edge of Darkness is played over a prologue followed by eight rounds. During the rounds, play is conducted in clockwise order, starting with the first player. In the prologue, players will draft exactly two advancements to sleeve into their Guild Starter cards. In the rounds, players will take turns ", "headingPath": "How to Play", "sharpsignalDocId": 1277}, {"page": 7, "score": 0.048131, "snippet": "For a diagram of setup, go to p.8/9. For your first game only : Before your first game you will need to sleeve all the Starter cards (Citizen and Patrician). Also, use one sleeve per Guild to hold all 7 of their Allegiance slips to keep them together and organized. For all future games you can just ", "headingPath": "Setup", "sharpsignalDocId": 1277}, {"page": 7, "score": 0.047371, "snippet": "When playing with less than 4 players, do not add the colored cubes of the Guild(s) not represented in the game. Leave them in the game box as they will not be used. There are 17 Neutral cards (11 Citizens and 6 Patricians). Some of them have a player requirement (seen on their Blight side). With 4 ", "headingPath": "Setup", "sharpsignalDocId": 1277}, {"page": 10, "score": 0.045262, "snippet": "The prologue plays differently from the regular rounds and gives players a head start into the game. The first player chooses any one advancement and sleeves it onto one of their four Guild Starter cards (See 'Sleeving Advancements' on this page). Important: They may then resolve the effect on the a", "headingPath": "Prologue", "sharpsignalDocId": 1277}, {"page": 11, "score": 0.03125, "snippet": "Drafting means selecting cards from the Street you want to add to your hand. A player must draft the rightmost card from the Street, unless they spend Influence to skip cards. When drafting, a player may pay Influence to skip one or more cards and draft the next available card(s) instead. For each c", "headingPath": "DRAFTING CARDS", "sharpsignalDocId": 1277}, {"page": 11, "score": 0.030303, "snippet": "Each round has two phases, described below. The first phase of a round is the Assembly Phase. During this phase, all players: Take cards from their Guild Hall and add them, City side up, to their hands. Important: When taking cards from their Guild Hall, players get all cards from their Guild Hall e", "headingPath": "Rounds · ASSEMBLY PHASE · Then in turn order each player:", "sharpsignalDocId": 1277}, {"page": 10, "score": 0.029851, "snippet": "The other three cards should be placed in the Discard pile along with the Neutral cards that were placed there during setup. Any player shuffles all the cards in the Discard pile to form a deck. In a fourplayer game this deck should have 26 cards; in a three-player game, 21; and in a two-player game", "headingPath": "Prologue", "sharpsignalDocId": 1277}, {"page": 16, "score": 0.029412, "snippet": "After you are done with all that you wished to do during your Action Phase, discard all the cards in your hand. If you discard a Neutral card , it goes to the Discard pile on the Game board. If you discard one of your cards , it goes to the Discard pile on the Game board. If you discard another play", "headingPath": "Discard (Mandatory) · End of Round", "sharpsignalDocId": 1277}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 10, "quote": null, "headingPath": "How to Play", "sharpsignalDocId": 1277}, {"page": 10, "quote": null, "headingPath": "Prologue", "sharpsignalDocId": 1277}, {"page": 10, "quote": null, "headingPath": "Prologue", "sharpsignalDocId": 1277}, {"page": 11, "quote": null, "headingPath": "Rounds · ASSEMBLY PHASE · Then in turn order each player:", "sharpsignalDocId": 1277}, {"page": 16, "quote": null, "headingPath": "Discard (Mandatory) · End of Round", "sharpsignalDocId": 1277}, {"page": 17, "quote": null, "headingPath": "Game End · Important: you can win the game by ¼ point. · EXAMPLE PLAYER GAME SCORING", "sharpsignalDocId": 1277}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1277 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1277 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 0.90279 of 2726 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 03:13 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 Edge of Darkness — Rulebook (corpus doc 1277) | How to Play | p.10 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Setup | p.7 | 0.048131 (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 Edge of Darkness — Rulebook (corpus doc 1277) | Setup | p.7 | 0.047371 (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 Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | 0.045262 (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 Edge of Darkness — Rulebook (corpus doc 1277) | DRAFTING CARDS | p.11 | 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 Edge of Darkness — Rulebook (corpus doc 1277) | Rounds · ASSEMBLY PHASE · Then in turn order each player: | p.11 | 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 Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | 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 Edge of Darkness — Rulebook (corpus doc 1277) | Discard (Mandatory) · End of Round | p.16 | 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 |
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 39 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 Edge of Darkness — Rulebook (corpus doc 1277) | How to Play | p.10 | #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 |
| #2 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Setup | p.7 | #3 | 0.047371 (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 Edge of Darkness — Rulebook (corpus doc 1277) | Discard (Mandatory) · End of Round | p.16 | #8 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Game End · Important: you can win the game by ¼ point. · EXAMPLE PLAYER GAME SCORING | p.17 | #16 | 0.014493 (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 Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | #4 | 0.045262 (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 |
| #6 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Rounds · ASSEMBLY PHASE · Then in turn order each player: | p.11 | #6 | 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 |
| #8 | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Setup | p.7 | #2 | 0.048131 (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
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 Edge of Darkness — Rulebook (corpus doc 1277) | How to Play | p.10 | no quote on the wire |
| [2] | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | no quote on the wire |
| [3] | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Prologue | p.10 | no quote on the wire |
| [4] | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Rounds · ASSEMBLY PHASE · Then in turn order each player: | p.11 | no quote on the wire |
| [5] | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Discard (Mandatory) · End of Round | p.16 | no quote on the wire |
| [6] | RULEBOOK Edge of Darkness — Rulebook (corpus doc 1277) | Game End · Important: you can win the game by ¼ point. · EXAMPLE PLAYER GAME SCORING | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 108 ms · first delta 3238 ms · total 11345 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 3898 ms · retrieval 108 ms · ask 7336 ms · gateway work 7447 ms · total 11345 ms
- tokens in (the prompt the answerer read)
- 3225
- tokens out (what the answerer generated)
- 822
- tok/sec
- 200.7 tok/sec — 822 output tokens in 4.095 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 12s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 3s 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 1207), 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.