You asked
When does the game end?
Answered counted as answeredAsked with: Viticulture Essential Editionbg-183394-en-1e
The game ends in the following ways: 1. At the end of the 7th year [1][2]. 2. When any player reaches or exceeds 20 victory points, the game finishes at the end of the current year (after year-end steps) [3][4][5].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 498 ms · ask 7430 ms · total 7949 ms
- single-flight (PR-5)
- queued 0 ms · generation 7949 ms
- retrieval refs (raw)
- [{"page": 18, "score": 0.04918, "snippet": "The game ends at the end of the 7th year. You win if your VP marker is ahead of the Automa VP marker. If they're on the same space, the game is a draw, and if the Automa is ahead, you lose.", "headingPath": "GamE End & WinninG/ losinG", "sharpsignalDocId": 90}, {"page": 17, "score": 0.047875, "snippet": "When any player reaches or exceeds 20 victory points, the game will finish at the end of the current year (after year-end steps). The player with the most points wins. In the case of a tie, tiebreakers are (in order): Most lira Total value of wine in the cellar Total value of grapes on the crush pad", "headingPath": "End GamE Goal and tiEbrEakErs", "sharpsignalDocId": 90}, {"page": 6, "score": 0.047643, "snippet": "Players age their grape and wine tokens, return workers to their vineyard mats, collect residual payments, remove rooster tokens from the wake-up chart, and rotate the first-player token counterclockwise. When any player reaches or exceeds 20 victory points, the game will finish at the end of the cu", "headingPath": "Year End", "sharpsignalDocId": 90}, {"page": 18, "score": 0.046394, "snippet": "Have more victory points (VPs) than the Automa at the end of the game, which consists of 7 years.", "headingPath": "Goal", "sharpsignalDocId": 90}, {"page": 17, "score": 0.03125, "snippet": "At the end of each year after all players have passed, players age grape and wine tokens, remove all workers from the board, collect any residual payments earned from filling orders, and rotate the first-player token counter-clockwise to the next player.", "headingPath": "yEar End", "sharpsignalDocId": 90}, {"page": 6, "score": 0.030303, "snippet": "Starting with the top player on the wake-up chart and proceeding down the chart, each player will place 1 worker on any available action space in the winter (blue action spaces) and then immediately take that action, or that player may choose to end their year by passing. This cycle of turns continu", "headingPath": "Winter", "sharpsignalDocId": 90}, {"page": 6, "score": 0.029851, "snippet": "Starting with the top player on the wake-up chart and proceeding down the chart, each player will either place 1 worker on any available action space in the summer (yellow action spaces) and then immediately take that action, or that player may choose to save their remaining workers for the winter b", "headingPath": "Summer", "sharpsignalDocId": 90}, {"page": 19, "score": 0.029762, "snippet": "You can play the game in campaign mode to add variation and challenge. The campaign mode consists of eight challenges, you must beat the Automa in each one to complete the campaign. Each time you lose, restart with the same challenge and begin with a number of bonus action tokens in hand equal to th", "headingPath": "campaiGn play", "sharpsignalDocId": 90}]
- citations (raw)
- [{"page": 18, "quote": null, "headingPath": "GamE End & WinninG/ losinG", "sharpsignalDocId": 90}, {"page": 18, "quote": null, "headingPath": "Goal", "sharpsignalDocId": 90}, {"page": 17, "quote": null, "headingPath": "End GamE Goal and tiEbrEakErs", "sharpsignalDocId": 90}, {"page": 1, "quote": null, "headingPath": "Goal", "sharpsignalDocId": 90}, {"page": 6, "quote": null, "headingPath": "Year End", "sharpsignalDocId": 90}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 90 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 90 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)
- debug row retained until
- Nov 3, 2026 13:40
retrieval — what the search arm returned
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 Viticulture Essential Edition — Rulebook (corpus doc 90) | GamE End & WinninG/ losinG | p.18 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 189 |
| #2 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | End GamE Goal and tiEbrEakErs | p.17 | 0.047875 (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 Viticulture Essential Edition — Rulebook (corpus doc 90) | Year End | p.6 | 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 |
| #4 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Goal | p.18 | 0.046394 (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)) | 97 |
| #5 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | yEar End | p.17 | 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)) | 254 |
| #6 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Winter | p.6 | 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 |
| #7 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Summer | p.6 | 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 |
| #8 | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | campaiGn play | p.19 | 0.029762 (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 |
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 Viticulture Essential Edition — Rulebook (corpus doc 90) | GamE End & WinninG/ losinG | p.18 | no quote on the wire |
| [2] | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Goal | p.18 | no quote on the wire |
| [3] | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | End GamE Goal and tiEbrEakErs | p.17 | no quote on the wire |
| [4] | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Goal | p.1 | no quote on the wire |
| [5] | RULEBOOK Viticulture Essential Edition — Rulebook (corpus doc 90) | Year End | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 498 ms · first delta 7432 ms · total 7949 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 498 ms · ask 7430 ms · gateway work 7949 ms · total 7949 ms
- tokens in (the prompt the answerer read)
- 1260
- tokens out (what the answerer generated)
- 68
- tok/sec
- 148.1 tok/sec — 68 output tokens in 0.459 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 12s ago)
- 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 21), 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.