You asked
How do I play?
Answered counted as answeredAsked with: Voidfallbg-337627-en-1e
The sage rests. The game continues.
🔧 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 5392 ms · total 5497 ms
- single-flight (PR-5)
- queued 0 ms · generation 5497 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048652, "snippet": "Voidfall is an epic game with many choices and almost infinite variability. Even if you regularly enjoy complex games, the number of choices in your first game might feel overwhelming. In order to teach the game while also letting you play it, we have created a tutorial scenario, which shows you the", "headingPath": "YOUR FIRST GAME AND TUTORIAL SCENARIO", "sharpsignalDocId": 278}, {"page": 6, "score": 0.047712, "snippet": "In order to play the tutorial, do the following in this order: Open the Compendium. Go to page 10, to the Setup chapter. 1 Follow the Setup instructions (ignoring the blue 'Co-op/Solo' sections). 2 Especially follow the additional tutorial instructions and examples for the Setup, shown in italic wit", "headingPath": "HOW TO PLAY THE TUTORIAL", "sharpsignalDocId": 278}, {"page": 9, "score": 0.047379, "snippet": "Each turn, you must select exactly one of your available Focus cards (from your hand), and play it. The cards on the Joint/Heroic Focus offer are also available. Place a Focus card from your hand into your discard pile to take and resolve a matching Joint/Heroic Focus card. To take a Leadership Focu", "headingPath": "1. SELECTION STEP 1", "sharpsignalDocId": 278}, {"page": 6, "score": 0.045831, "snippet": "Welcome to Voidfall! If this is the first time you play this game, you are in the right place! There are three booklets in the box that have different uses. The Rulebook -which you are now reading-contains the list of components, the game structure (page 7), and how all the systems of the game work ", "headingPath": "HOW TO USE THE BOOKLETS · GAME MODES AND COLORING", "sharpsignalDocId": 278}, {"page": 1, "score": 0.044589, "snippet": "Components, Cycle of Play, & Rules of Play RULEBOOK", "headingPath": "START HERE!", "sharpsignalDocId": 278}, {"page": 7, "score": 0.04374, "snippet": "! Note: The setup can be found in the Compendium, page 10. Each game of Voidfall is composed of 3 Cycles. Each Cycle has three Phases in this order: Preparation Phase A Focus Phase B Evaluation Phase C The steps of this phase are summarized on the left and top part of the Galactic board ( blue numbe", "headingPath": "Cycle of Play · A - PREPARATION PHASE A", "sharpsignalDocId": 278}, {"page": 14, "score": 0.030769, "snippet": "Anytime you would be required to place a 4 th Catastrophe token during this step, you immediately lose the game. Once you have finished your turn completely, the next player in T urn Order takes their complete turn in a similar fashion. After every player has taken their turn, proceed with the next ", "headingPath": "THE VOID ADVANCES STEP", "sharpsignalDocId": 278}, {"page": 32, "score": 0.030366, "snippet": "When you gain an Agenda, you do the following: Select one of the four Agenda types: Dominance, Wealth, Might, or Support. 1 ! Note: The Agenda type is sometimes specified by the icon of the effect. Choose one of these two options: 2 Take one of the visible Agendas of the selected type from the Agend", "headingPath": "AGENDAS", "sharpsignalDocId": 278}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "HOW TO PLAY THE TUTORIAL", "sharpsignalDocId": 278}, {"page": 9, "quote": null, "headingPath": "1. SELECTION STEP 1", "sharpsignalDocId": 278}, {"page": 10, "quote": null, "headingPath": "2. ACTIONS STEP 2", "sharpsignalDocId": 278}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 278 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 278 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 0.91772 of 1264 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 28, 2026 11:51 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 Voidfall — Rulebook (corpus doc 278) | YOUR FIRST GAME AND TUTORIAL SCENARIO | p.6 | 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 |
| #2 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | HOW TO PLAY THE TUTORIAL | p.6 | 0.047712 (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 Voidfall — Rulebook (corpus doc 278) | 1. SELECTION STEP 1 | p.9 | 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 |
| #4 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | HOW TO USE THE BOOKLETS · GAME MODES AND COLORING | p.6 | 0.045831 (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 Voidfall — Rulebook (corpus doc 278) | START HERE! | p.1 | 0.044589 (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)) | 51 |
| #6 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | Cycle of Play · A - PREPARATION PHASE A | p.7 | 0.04374 (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 Voidfall — Rulebook (corpus doc 278) | THE VOID ADVANCES STEP | p.14 | 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 |
| #8 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | AGENDAS | p.32 | 0.030366 (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 79 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 Voidfall — Rulebook (corpus doc 278) | HOW TO PLAY THE TUTORIAL | p.6 | #2 | 0.047712 (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 Voidfall — Rulebook (corpus doc 278) | 2. ACTIONS STEP 2 | p.10 | #11 | 0.028543 (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 Voidfall — Rulebook (corpus doc 278) | PRE-SELECTED FOCUS VARIANT | p.14 | #12 | 0.027984 (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 Voidfall — Rulebook (corpus doc 278) | HOW TO USE THE BOOKLETS · GAME MODES AND COLORING | p.6 | #4 | 0.045831 (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 |
| #5 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | JOINT FOCUS EFFECTS | p.11 | #18 | 0.022918 (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 Voidfall — Rulebook (corpus doc 278) | YOUR FIRST GAME AND TUTORIAL SCENARIO | p.6 | #1 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | AGENDAS | p.32 | #8 | 0.030366 (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 |
| #8 | RULEBOOK Voidfall — Rulebook (corpus doc 278) | 1. SELECTION STEP 1 | p.9 | #3 | 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)) | 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 Voidfall — Rulebook (corpus doc 278) | HOW TO PLAY THE TUTORIAL | p.6 | no quote on the wire |
| [2] | RULEBOOK Voidfall — Rulebook (corpus doc 278) | 1. SELECTION STEP 1 | p.9 | no quote on the wire |
| [3] | RULEBOOK Voidfall — Rulebook (corpus doc 278) | 2. ACTIONS STEP 2 | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 102 ms · first delta 3549 ms · total 5497 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 102 ms · ask 5392 ms · gateway work 5497 ms · total 5497 ms
- tokens in (the prompt the answerer read)
- 2823
- tokens out (what the answerer generated)
- 386
- tok/sec
- 203.2 tok/sec — 386 output tokens in 1.900 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 18s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 9s 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 206), 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.