You asked
When does the game end?
Answered counted as answeredAsked with: Wilderness Warbg-1822-en-1e
That settles it — whose turn was it?
🔧 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 225 ms · ask 6895 ms · total 7126 ms
- single-flight (PR-5)
- queued 0 ms · generation 7126 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "Exception: When a player has one card left, he may announce that he will pass and hold his card. The held card, if applicable, may be played as an Event during an enemy Action Phase [5.5.6] or held until the following season. If held until the following season, the player must play ALL his cards tha", "headingPath": "A. Early Season · B. Late Season · 5.1 General", "sharpsignalDocId": 1188}, {"page": 15, "score": 0.046432, "snippet": "13.11 Sudden Death. Check during each Victory Check Phase (4.0 B.6) to see if any of these conditions prevail: If the British control [2.0] all fortresses plus solely occupy Niagara and Ohio Forks, they win regardless of VPs. If either side has 11 or more VPs, it wins. After 1759, the French win if ", "headingPath": "13.1 How to Win · 13.2 Victory Points", "sharpsignalDocId": 1188}, {"page": 4, "score": 0.046154, "snippet": "5.21 Both players are dealt cards from a single, facedown draw pile. The scenario instructions state how many cards players receive. 5.22 As cards are played, they are placed into a faceup discard pile. Certain Events allow a player to draw a card from the discard pile into his hand. 5.23 If a card ", "headingPath": "5.2 Card Deck", "sharpsignalDocId": 1188}, {"page": 11, "score": 0.032258, "snippet": "Either side's leaders may be killed (removed from the game). If you roll a natural '1' or '6' (before DRMs) AND cause at least one step loss, the opposing player must roll a die for EACH of his leaders involved in the Battle. A roll of '1' for any leader kills him. If only one side has surviving uni", "headingPath": "7.7 Leader Losses · 7.8 Winner/Loser", "sharpsignalDocId": 1188}, {"page": 15, "score": 0.031746, "snippet": "In tournaments, or if players both want to play the same side, each player should write down a bid of at least 0 VPs. The higher bidder plays the favored side. The other player begins with the number of VPs bid by the opponent added to the scenario-defined start level. If both players bid the same, ", "headingPath": "13.3 Bidding", "sharpsignalDocId": 1188}, {"page": 3, "score": 0.03125, "snippet": "A.1 Deal Cards. Deal each player cards as specified in the sce -nario set up. Events during the game can change the number of cards players receive. A.2 Action Phases. Beginning with the French, players alternate taking Action Phases. Each Action Phase consists of playing a card to activate leaders ", "headingPath": "A. Early Season", "sharpsignalDocId": 1188}, {"page": 13, "score": 0.030159, "snippet": "The Attacker must cause a HIGHER enemy step loss result to win an Assault, otherwise the Defender wins. Eliminating all defending units is NOT sufficient to win: unoccupied forts and fortresses continued to defend themselves on the 0 column of the CRT. 9.21 If the defender wins, the Siege continues.", "headingPath": "9.2 Winner/Loser · 10.0 RAIDS · 10.1 Targets", "sharpsignalDocId": 1188}, {"page": 14, "score": 0.029851, "snippet": "Apply the following losses to each affected stack: ~ First, eliminate half (rounded up) of the reduced Drilled Troops units (owner's choice). Second, reduce EVERY full-strength Drilled Troops unit. Exception: The last friendly step in a space (i.e., a lone, reduced unit) is never removed by Attritio", "headingPath": "11.2 Attrition Losses", "sharpsignalDocId": 1188}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "A. Early Season · B. Late Season · 5.1 General", "sharpsignalDocId": 1188}, {"page": 15, "quote": null, "headingPath": "13.1 How to Win · 13.2 Victory Points", "sharpsignalDocId": 1188}, {"page": 11, "quote": null, "headingPath": "7.7 Leader Losses · 7.8 Winner/Loser", "sharpsignalDocId": 1188}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1188 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1188 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 0.90415 of 939 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 18, 2026 17:11 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 Wilderness War — Rulebook (corpus doc 1188) | A. Early Season · B. Late Season · 5.1 General | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 13.1 How to Win · 13.2 Victory Points | p.15 | 0.046432 (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 Wilderness War — Rulebook (corpus doc 1188) | 5.2 Card Deck | p.4 | 0.046154 (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 Wilderness War — Rulebook (corpus doc 1188) | 7.7 Leader Losses · 7.8 Winner/Loser | p.11 | 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 |
| #5 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 13.3 Bidding | p.15 | 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 |
| #6 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | A. Early Season | p.3 | 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 |
| #7 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 9.2 Winner/Loser · 10.0 RAIDS · 10.1 Targets | p.13 | 0.030159 (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 Wilderness War — Rulebook (corpus doc 1188) | 11.2 Attrition Losses | p.14 | 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 46 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 Wilderness War — Rulebook (corpus doc 1188) | p.1 | #37 | 0.010417 (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 | |
| #2 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 13.1 How to Win · 13.2 Victory Points | p.15 | #2 | 0.046432 (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 Wilderness War — Rulebook (corpus doc 1188) | 7.7 Leader Losses · 7.8 Winner/Loser | p.11 | #4 | 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 |
| #4 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | p.1 | #32 | 0.010989 (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 Wilderness War — Rulebook (corpus doc 1188) | p.1 | #17 | 0.013158 (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 Wilderness War — Rulebook (corpus doc 1188) | A. Early Season | p.3 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | A. Early Season · B. Late Season · 5.1 General | p.4 | #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 |
| #8 | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | Table of Contents | p.1 | #30 | 0.011236 (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 |
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 Wilderness War — Rulebook (corpus doc 1188) | A. Early Season · B. Late Season · 5.1 General | p.4 | no quote on the wire |
| [2] | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 13.1 How to Win · 13.2 Victory Points | p.15 | no quote on the wire |
| [3] | RULEBOOK Wilderness War — Rulebook (corpus doc 1188) | 7.7 Leader Losses · 7.8 Winner/Loser | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 225 ms · first delta 5449 ms · total 7126 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 225 ms · ask 6895 ms · gateway work 7126 ms · total 7126 ms
- tokens in (the prompt the answerer read)
- 3518
- tokens out (what the answerer generated)
- 312
- tok/sec
- 194.3 tok/sec — 312 output tokens in 1.606 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 14s 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 1118), 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.