You asked
How do I play?
Answered counted as answeredAsked with: Bonfirebg-304420-en-1e
The table has its answer — dice up.
🔧 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 110 ms · ask 4924 ms · total 5036 ms
- single-flight (PR-5)
- queued 0 ms · generation 5036 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.048916, "snippet": "You will play a 2-player game against \"Tom\" (which is short for \"AuTOMatic Player\"), a virtual player who uses a modified set of rules. He performs actions determined by a deck of cards in order to score Points. Your goal is to score more Points than Tom. All rules of a 2-player game apply for Solo ", "headingPath": "SOLO PLAY · SETUP · COURSE OF THE GAME", "sharpsignalDocId": 523}, {"page": 13, "score": 0.047643, "snippet": "The Countdown Phase begins when the 7th Novice is placed in the High Council. However, the game ends prematurely, if Tom played through his entire deck of cards for the 4th time (you do not need to count: When Tom takes his last Portal, he is in the 4th playthrough of his deck). Proceed to the Final", "headingPath": "END OF SOLO PLAY · CHALLENGE 1: HANDICAP MODE · Appendix I : TAsks · taSkS wIth 2-3 PoIntS, Blue BonfIreS · taSkS wIth 4-5 PoIntS, red BonfIreS", "sharpsignalDocId": 523}, {"page": 6, "score": 0.047371, "snippet": "Here we provide a rough overview of the game; a more detailed description will follow in the next chapters. You alternate taking single turns in clockwise order (Page 7 onward, a PlayEr's Turn ). During the course of the game your will receive and fulfill Tasks (Page 9, rEcEivE a Task ). With a fulf", "headingPath": "GAME OVERVIEW · HOW DOES THE GAME PLAY? · WHAT CAN I DO ON MY TURN? · HOW DO I GAIN POINTS?", "sharpsignalDocId": 523}, {"page": 4, "score": 0.045724, "snippet": "When playing Bonfire for the first time, I recommend to place Tasks of different colors on each island. GAME BOARD The game is mostly independent of the player count. The exceptions are emphasized in green writing and summarized here: • Number of Tasks (Page 4, Step 2) • Number of Portals in a 1 or ", "headingPath": "", "sharpsignalDocId": 523}, {"page": 5, "score": 0.032258, "snippet": "Place your Player Board in front of you. Attach a Starting Tile for Guardians to your Player Board and place your Guardian onto it. 1 of the players: Take 1 Extension for each player (making sure the one with the oval Building is among them) and distribute 1 to each player at random. Every player: A", "headingPath": "PLAYER BOARDS", "sharpsignalDocId": 523}, {"page": 8, "score": 0.030769, "snippet": "With the help of your Ship, you can move to 2 different types of islands: Those where you can retrieve Guardians and those where you can receive Tasks. When you move your Ship for the first time in a game, pay 1 Action Tile to move to any island of your choice. The next time, when you move your Ship", "headingPath": "Move your ShIP", "sharpsignalDocId": 523}, {"page": 7, "score": 0.030303, "snippet": "On each of your turns, perform 1 of the following options I , II , or III . Additionally, you may perform Bonus Actions if you fulfill a corresponding Common Task (Page 11, Bonus acTion) . These options are also depicted on your Action Overview: Special case: If you are no longer able to perform any", "headingPath": "A PLAYER'S TURN · I. PLACE A FATE TILE AND GAIN ACTION TILES", "sharpsignalDocId": 523}, {"page": 9, "score": 0.029412, "snippet": "'Bring us the treasures of the world to show that you care about the land. We shall give you tasks, so that you yourself shall grow,' said the Guardians. On the islands you can receive Tasks. The front of each Task shows a condition to be met and the Points you may gain if you fulfill it. The back, ", "headingPath": "Move your ShIP · receIve a taSk · a) Pay Action Tile(s) · b) Pay Resources · c) Deliver the Offering Tiles and receive the Task", "sharpsignalDocId": 523}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "GAME OVERVIEW · HOW DOES THE GAME PLAY? · WHAT CAN I DO ON MY TURN? · HOW DO I GAIN POINTS?", "sharpsignalDocId": 523}, {"page": 7, "quote": null, "headingPath": "A PLAYER'S TURN · I. PLACE A FATE TILE AND GAIN ACTION TILES", "sharpsignalDocId": 523}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 523 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 523 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 0.91519 of 1238 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 28, 2026 12:42 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 Bonfire — Rulebook (corpus doc 523) | SOLO PLAY · SETUP · COURSE OF THE GAME | p.12 | 0.048916 (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 Bonfire — Rulebook (corpus doc 523) | END OF SOLO PLAY · CHALLENGE 1: HANDICAP MODE · Appendix I : TAsks · taSkS wIth 2-3 PoIntS, Blue BonfIreS · taSkS wIth 4-5 PoIntS, red BonfIreS | p.13 | 0.047643 (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 Bonfire — Rulebook (corpus doc 523) | GAME OVERVIEW · HOW DOES THE GAME PLAY? · WHAT CAN I DO ON MY TURN? · HOW DO I GAIN POINTS? | p.6 | 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 Bonfire — Rulebook (corpus doc 523) | p.4 | 0.045724 (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 Bonfire — Rulebook (corpus doc 523) | PLAYER BOARDS | 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 |
| #6 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | Move your ShIP | p.8 | 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 Bonfire — Rulebook (corpus doc 523) | A PLAYER'S TURN · I. PLACE A FATE TILE AND GAIN ACTION TILES | p.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)) | 300 |
| #8 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | Move your ShIP · receIve a taSk · a) Pay Action Tile(s) · b) Pay Resources · c) Deliver the Offering Tiles and receive the Task | p.9 | 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 36 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 Bonfire — Rulebook (corpus doc 523) | GAME OVERVIEW · HOW DOES THE GAME PLAY? · WHAT CAN I DO ON MY TURN? · HOW DO I GAIN POINTS? | p.6 | #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 |
| #2 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | SOLO PLAY · SETUP · COURSE OF THE GAME | p.12 | #1 | 0.048916 (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 Bonfire — Rulebook (corpus doc 523) | Tips for the first game: | p.6 | #18 | 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 |
| #4 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | p.2 | #12 | 0.026133 (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 Bonfire — Rulebook (corpus doc 523) | p.2 | #19 | 0.014286 (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 | |
| #6 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | A PLAYER'S TURN · I. PLACE A FATE TILE AND GAIN ACTION TILES | p.7 | #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 |
| #7 | RULEBOOK Bonfire — Rulebook (corpus doc 523) | p.4 | #4 | 0.045724 (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 Bonfire — Rulebook (corpus doc 523) | PLAYER BOARDS | p.5 | #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)) | vector + 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 Bonfire — Rulebook (corpus doc 523) | GAME OVERVIEW · HOW DOES THE GAME PLAY? · WHAT CAN I DO ON MY TURN? · HOW DO I GAIN POINTS? | p.6 | no quote on the wire |
| [2] | RULEBOOK Bonfire — Rulebook (corpus doc 523) | A PLAYER'S TURN · I. PLACE A FATE TILE AND GAIN ACTION TILES | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 110 ms · first delta 3182 ms · total 5036 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 110 ms · ask 4924 ms · gateway work 5036 ms · total 5036 ms
- tokens in (the prompt the answerer read)
- 2974
- tokens out (what the answerer generated)
- 364
- tok/sec
- 201.8 tok/sec — 364 output tokens in 1.804 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 43s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 2s 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 454), 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.