You asked
How do I play?
Answered counted as answeredAsked with: Keep the Heroes Out!bg-333255-en-1e
So says the rulebook. So plays the table.
🔧 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 200 ms · ask 4337 ms · total 4540 ms
- single-flight (PR-5)
- queued 0 ms · generation 4540 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048916, "snippet": "During your turn complete the following 5 phases, in order: 1) Play cards from your hand, 2) Refresh Loot, 3) Clean Up and Upkeep, 4) Heroes Invasion, 5) End your turn. Play cards from your hand: Cards must be played one at a time. To play a card, choose one from your hand, reveal it, resolve its ac", "headingPath": "Player's Turn", "sharpsignalDocId": 453}, {"page": 16, "score": 0.047883, "snippet": "In your turn you will need to complete the following 5 phases in order: 1) Play cards from your hand, 2) Refresh Loot, 3) Clean Up and Upkeep, 4) Heroes Invasion, 5) End your turn. 1 2 Refresh Loot 3 Clean Up and Upkeep Heroes Invasion Play cards from your hand Important: In a 4 player game, for exa", "headingPath": "Player's Turn · Actions · Draw: · Place a resource: · Choose wisely: · Activate: · …", "sharpsignalDocId": 453}, {"page": 12, "score": 0.046642, "snippet": "12 This example covers a complete turn of the Ratkin player. Pla yer's Turn ExamplePla yer's Turn Example Phase 1: Play cards from your hand 1) At the start of their turn, the Ratkin player decides to push their luck by sending a Hero to the Cells to draw 3 extra cards. The Hero revealed is a Warrio", "headingPath": "", "sharpsignalDocId": 453}, {"page": 12, "score": 0.046635, "snippet": "This example covers a complete turn of the Ratkin player. 3.1) The player then plays their second card. This one also gives two choices, and they choose the left side gaining two Activate actions. First they Activate the Sewers and place a Frog, and then; 3.2) Activate the Workshop to place a Trap. ", "headingPath": "Player's Turn Example", "sharpsignalDocId": 453}, {"page": 13, "score": 0.046244, "snippet": "5) For their fourth card, the player chooses the Swarm and moves two of their Monsters from the Sewers to the Apothecary, bringing the Frog token along with them. 6) The player then plays their fi fth card, choosing the Move action to move their Monster from the Workshop to the Beast trainer, bringi", "headingPath": "Player's Turn Example · Phase 2: Refresh Loot · Phase 3: Clean Up and Upkeep", "sharpsignalDocId": 453}, {"page": 6, "score": 0.043636, "snippet": "Unless otherwise stated, actions are resolved individually, in any order you choose, splitting the actions depicted in one card to one or more of your Monsters in the Dungeon. You may also choose not to use all the actions depicted in a card. If an action requires a Token and there are no more left ", "headingPath": "Actions · Draw: · Choose wisely: · Activate: · Defend: · Surge: · …", "sharpsignalDocId": 453}, {"page": 8, "score": 0.043496, "snippet": "Once per turn, at any point of your turn, you may push your luck by throwing a Hero in the Cells! To perform this action you do NOT need to have one of your Monsters in the Cells room nor do you need to resolve an Activate action. First draw the top card from the Guild deck. If you draw a scenario c", "headingPath": "Special Room: Cells", "sharpsignalDocId": 453}, {"page": 5, "score": 0.031746, "snippet": "If you reached the end of the second wave's Guild deck, then CONGRATULATIONS, you all win the game! If at any time, your Treasure Token with value 4 is plundered, then you immediately lose the game! End your turn: After the end of a Heroes Invasion, if the game hasn't fi nished, the active player pa", "headingPath": "Player's Turn", "sharpsignalDocId": 453}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "Player's Turn", "sharpsignalDocId": 453}, {"page": 16, "quote": null, "headingPath": "Player's Turn · Actions · Draw: · Place a resource: · Choose wisely: · Activate: · …", "sharpsignalDocId": 453}, {"page": 5, "quote": null, "headingPath": "Player's Turn", "sharpsignalDocId": 453}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 453 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 453 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 0.92491 of 1638 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 27, 2026 05:38 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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | 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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn · Actions · Draw: · Place a resource: · Choose wisely: · Activate: · … | p.16 | 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 |
| #3 | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | p.12 | 0.046642 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn Example | p.12 | 0.046635 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn Example · Phase 2: Refresh Loot · Phase 3: Clean Up and Upkeep | p.13 | 0.046244 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Actions · Draw: · Choose wisely: · Activate: · Defend: · Surge: · … | p.6 | 0.043636 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Special Room: Cells | p.8 | 0.043496 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | 0.031746 (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 27 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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | #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 |
| #2 | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn Example | p.12 | #4 | 0.046635 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn Example · Phase 2: Refresh Loot · Phase 3: Clean Up and Upkeep | p.13 | #5 | 0.046244 (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 |
| #4 | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | p.12 | #3 | 0.046642 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | #8 | 0.031746 (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 |
| #6 | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | Special Room: Laboratory | p.8 | #10 | 0.027778 (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 |
| #7 | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | Actions · Draw: · Choose wisely: · Activate: · Defend: · Surge: · … | p.6 | #6 | 0.043636 (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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn · Actions · Draw: · Place a resource: · Choose wisely: · Activate: · … | p.16 | #2 | 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 |
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 Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | no quote on the wire |
| [2] | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn · Actions · Draw: · Place a resource: · Choose wisely: · Activate: · … | p.16 | no quote on the wire |
| [3] | RULEBOOK Keep the Heroes Out! — Rulebook (corpus doc 453) | Player's Turn | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 200 ms · first delta 1993 ms · total 4540 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 200 ms · ask 4337 ms · gateway work 4540 ms · total 4540 ms
- tokens in (the prompt the answerer read)
- 3211
- tokens out (what the answerer generated)
- 503
- tok/sec
- 202.2 tok/sec — 503 output tokens in 2.488 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, 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 383), 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.