You asked
How do I play?
Answered counted as answeredAsked with: Bullet★bg-343844-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 103 ms · ask 4595 ms · total 6238 ms
- single-flight (PR-5)
- queued 1536 ms · generation 4702 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.047643, "snippet": "These examples assume a solo game. (Top Left) 6 bullets were sent, which is enough to break a shield. (Top right) Only 4 bullets were sent, which doesn't break a shield. They remain in the Boss' incoming. (Bottom) 10 bullets were sent, which is two short of breaking two shields. 3. Each heroine puts", "headingPath": "On Boss Difficulty · Losing · Winning · 5-8 Players", "sharpsignalDocId": 1281}, {"page": 9, "score": 0.046898, "snippet": "Players form teams of two, sitting next to each other and across from another team. No timer is used in this mode. Powerups are not used in this mode. During Setup, each player takes a set of 3 Team Actions and places them in their powerup slots. These have AP costs and can be used by either heroine", "headingPath": "Team mode plays like Free-ForAll, with a few differences:", "sharpsignalDocId": 1281}, {"page": 9, "score": 0.045695, "snippet": "Once all Heroines have finished their End Phases: Draw new powerups to the middle of the table until there are powerups equal to the number of heroines. If you run out of powerups, shuffle the powerup discard to form a new deck. Increase the intensity by 1, plus 1 for each heroine that lost this tur", "headingPath": "Cleanup Phase · Game End · Sudden Death · Additional Modes", "sharpsignalDocId": 1281}, {"page": 6, "score": 0.032787, "snippet": "Turns are simultaneous, with each heroine performing the Option Phase then End Phase at their own pace. A heroine cannot enter the End Phase until their current bag is empty. Once all Heroines have performed both of these phases, a Cleanup Phase occurs, then a new round begins. Send as many bullets ", "headingPath": "Gameplay · Option Phase · Place Bullets · Use Actions", "sharpsignalDocId": 1281}, {"page": 10, "score": 0.032258, "snippet": "No timer is used in this mode. Powerups are not used in this mode. Each player chooses a heroine board. Take an AP Marker and place it on the highest space of your AP Track. Take all patterns associated with your Heroine and shuffle them, then draw three and put them face-up in front of you, under y", "headingPath": "Setup", "sharpsignalDocId": 1281}, {"page": 4, "score": 0.030415, "snippet": "Each girl is the heroine of their own story, each with something to prove. Choose a heroine and use their unique ability and actions to prove you have what it takes to win! Each heroine has their own unique player board that changes how they play the game. Each heroine consists of a heroine board an", "headingPath": "Heroines · Heroines have the following attributes: · Bullets · Each bullet has the following attributes: · Patterns", "sharpsignalDocId": 1281}, {"page": 8, "score": 0.030303, "snippet": "(Left) A pattern with any bullet as requirements. (Middle) A pattern with the two edges needing the same numbered bullet. (Right) A pattern with a colored bullet and any bullet as requirements. Empty Space : A dotted-line circle indicates that this space must have nothing in it. This includes bullet", "headingPath": "Use Patterns · Additional Components · Use Powerups · End Phase", "sharpsignalDocId": 1281}, {"page": 5, "score": 0.029851, "snippet": "Powerups give heroines a temporary boost. Each powerup has an effect. All powerups are a one-time use and are discarded when used. In a heated firefight, bullets are always coming at you from all angles! each Heroine will draw at the end of their round The Intensity Track denotes how many bullets in", "headingPath": "Powerups · Intensity · Center and Current Bags · Setup · Interacting With the Center or Current", "sharpsignalDocId": 1281}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "Overview · Designer's Forward", "sharpsignalDocId": 1281}, {"page": 6, "quote": null, "headingPath": "Gameplay · Option Phase · Place Bullets · Use Actions", "sharpsignalDocId": 1281}, {"page": 9, "quote": null, "headingPath": "Cleanup Phase · Game End · Sudden Death · Additional Modes", "sharpsignalDocId": 1281}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1281 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1281 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 0.91237 of 2054 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 15:42 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 Bullet★ — Rulebook (corpus doc 1281) | On Boss Difficulty · Losing · Winning · 5-8 Players | p.12 | 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 |
| #2 | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Team mode plays like Free-ForAll, with a few differences: | p.9 | 0.046898 (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 Bullet★ — Rulebook (corpus doc 1281) | Cleanup Phase · Game End · Sudden Death · Additional Modes | p.9 | 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 |
| #4 | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Gameplay · Option Phase · Place Bullets · Use Actions | p.6 | 0.032787 (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 Bullet★ — Rulebook (corpus doc 1281) | Setup | p.10 | 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 Bullet★ — Rulebook (corpus doc 1281) | Heroines · Heroines have the following attributes: · Bullets · Each bullet has the following attributes: · Patterns | p.4 | 0.030415 (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 Bullet★ — Rulebook (corpus doc 1281) | Use Patterns · Additional Components · Use Powerups · End Phase | p.8 | 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 Bullet★ — Rulebook (corpus doc 1281) | Powerups · Intensity · Center and Current Bags · Setup · Interacting With the Center or Current | p.5 | 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 |
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 18 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 Bullet★ — Rulebook (corpus doc 1281) | Team mode plays like Free-ForAll, with a few differences: | p.9 | #2 | 0.046898 (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 Bullet★ — Rulebook (corpus doc 1281) | Heroines · Heroines have the following attributes: · Bullets · Each bullet has the following attributes: · Patterns | p.4 | #6 | 0.030415 (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 Bullet★ — Rulebook (corpus doc 1281) | Overview · Designer's Forward | p.2 | #15 | 0.013699 (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 Bullet★ — Rulebook (corpus doc 1281) | Presented by Level 99 Games | p.2 | #12 | 0.028958 (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 Bullet★ — Rulebook (corpus doc 1281) | Setup · Gameplay · Heroine Round · Boss Round | p.11 | #13 | 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 |
| #6 | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Gameplay · Option Phase · Place Bullets · Use Actions | p.6 | #4 | 0.032787 (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 Bullet★ — Rulebook (corpus doc 1281) | Cleanup Phase · Game End · Sudden Death · Additional Modes | p.9 | #3 | 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 |
| #8 | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Setup | p.10 | #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 Bullet★ — Rulebook (corpus doc 1281) | Overview · Designer's Forward | p.2 | no quote on the wire |
| [2] | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Gameplay · Option Phase · Place Bullets · Use Actions | p.6 | no quote on the wire |
| [3] | RULEBOOK Bullet★ — Rulebook (corpus doc 1281) | Cleanup Phase · Game End · Sudden Death · Additional Modes | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 103 ms · first delta 1567 ms · total 6238 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1536 ms · retrieval 103 ms · ask 4595 ms · gateway work 4702 ms · total 6238 ms
- tokens in (the prompt the answerer read)
- 3280
- tokens out (what the answerer generated)
- 610
- tok/sec
- 201.1 tok/sec — 610 output tokens in 3.034 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 6s 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 1211), 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.