You asked
When does the game end?
Answered counted as answeredAsked with: Québecbg-91984-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 1892 ms · total 1996 ms
- single-flight (PR-5)
- queued 0 ms · generation 1996 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048652, "snippet": "The game ends after the fourth century. No ★ tokens are placed on buildings on which there is an architect at the end of the last century. These buildings remain in play, as is, with the workers on them. First, do a regular end of a century scoring round, including completing the neutral architect's", "headingPath": "Final scoring · End of the game", "sharpsignalDocId": 208}, {"page": 3, "score": 0.047712, "snippet": "A century immediately ends when one of these two conditions is met: A player does not have any workers in front of him (active or passive) at the beginning of his turn. When a player does the Start a new building action and there are no more available buildings for the current century . At the end o", "headingPath": "End of a century", "sharpsignalDocId": 208}, {"page": 4, "score": 0.046898, "snippet": "If the century ended with a player moving his architect (condition 2), this player finishes his turn by placing his architect on a new building and activating his workers. The game then continues normally. EXCEPTION : If a player ended the century by moving the neutral architect, he does not finish ", "headingPath": "End of a century · Scoring the zones of power Family rules - Skip if playing the complete rules", "sharpsignalDocId": 208}, {"page": 6, "score": 0.044557, "snippet": "As with the players' architects, it is possible to end a century when there are no more available buildings for the neutral architect this century. If a century ends in such a way, the active player will get to place the neutral architect at the beginning of the next century. If you would like to le", "headingPath": "Precisions · The History Québec City", "sharpsignalDocId": 208}, {"page": 5, "score": 0.03125, "snippet": "Conscription Crisis (1917) : At the end of the century but before the scoring round, players must remove their workers from each zone in which they have 2 workers or less. First Official Edition of the Québec Winter Carnival (1955) : At the end of the century but before the scoring round, each playe", "headingPath": "IV - 1908 - A World Heritage Site", "sharpsignalDocId": 208}, {"page": 4, "score": 0.030769, "snippet": "Score each zone, one after the other. Start with the Citadelle , then move to the century's most influencial zone and continue clockwise until all 5 zones have been scored. The most influencial zone for each century is: 1608 - Religion (purple); 1708 - Politics (red); 1808 - Economy (yellow); 1908 -", "headingPath": "Scoring the zones of power Complete rules", "sharpsignalDocId": 208}, {"page": 4, "score": 0.030303, "snippet": "What follows is an example of a complete scoring round with the complete rules. In it, you will see the various rules at play during a scoring round and how beneficial cascades are. It is the end of the first century . At the Citadelle, there are 5 black workers and 1 white. White scores 1 point and", "headingPath": "Example - Scoring the zones of power", "sharpsignalDocId": 208}, {"page": 3, "score": 0.029572, "snippet": "This will often be the first action you take in the game. Buildings completed with your architect give you VPs at the end of the game (see Final scoring , page 7). This action is also the best way to activate workers. At first, your architect is not in play. To put it in play, you must do the follow", "headingPath": "1. Start a new building", "sharpsignalDocId": 208}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Final scoring · End of the game", "sharpsignalDocId": 208}, {"page": 1, "quote": null, "headingPath": "Goal · Overview", "sharpsignalDocId": 208}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 208 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 208 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 0.82051 of 39 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 4, 2026 15:16 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 Québec — Rulebook (corpus doc 208) | Final scoring · End of the game | p.4 | 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 Québec — Rulebook (corpus doc 208) | End of a century | p.3 | 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 Québec — Rulebook (corpus doc 208) | End of a century · Scoring the zones of power Family rules - Skip if playing the complete rules | p.4 | 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 |
| #4 | RULEBOOK Québec — Rulebook (corpus doc 208) | Precisions · The History Québec City | p.6 | 0.044557 (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 Québec — Rulebook (corpus doc 208) | IV - 1908 - A World Heritage Site | p.5 | 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 |
| #6 | RULEBOOK Québec — Rulebook (corpus doc 208) | Scoring the zones of power Complete rules | p.4 | 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 Québec — Rulebook (corpus doc 208) | Example - Scoring the zones of power | p.4 | 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 Québec — Rulebook (corpus doc 208) | 1. Start a new building | p.3 | 0.029572 (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 24 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 Québec — Rulebook (corpus doc 208) | Final scoring · End of the game | p.4 | #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 |
| #2 | RULEBOOK Québec — Rulebook (corpus doc 208) | End of a century · Scoring the zones of power Family rules - Skip if playing the complete rules | p.4 | #3 | 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 |
| #3 | RULEBOOK Québec — Rulebook (corpus doc 208) | Precisions · The History Québec City | p.6 | #4 | 0.044557 (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 Québec — Rulebook (corpus doc 208) | Precisions · Strategic hints | p.6 | #9 | 0.029469 (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 Québec — Rulebook (corpus doc 208) | Goal · Overview | p.1 | #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 |
| #6 | RULEBOOK Québec — Rulebook (corpus doc 208) | IV - 1908 - A World Heritage Site | p.5 | #5 | 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 Québec — Rulebook (corpus doc 208) | 1. Start a new building | p.3 | #8 | 0.029572 (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 Québec — Rulebook (corpus doc 208) | End of a century | p.3 | #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 |
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 Québec — Rulebook (corpus doc 208) | Final scoring · End of the game | p.4 | no quote on the wire |
| [2] | RULEBOOK Québec — Rulebook (corpus doc 208) | Goal · Overview | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 102 ms · first delta 1868 ms · total 1996 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 1892 ms · gateway work 1996 ms · total 1996 ms
- tokens in (the prompt the answerer read)
- 3819
- tokens out (what the answerer generated)
- 14
- tok/sec
- 194.4 tok/sec — 14 output tokens in 0.072 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 36s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 5s 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 133), 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.