You asked
How do I take my turn?
Answered counted as answeredIn turn order (clockwise from the icon at the top of the track), you must choose one of the following two options: 1. Place a summer worker, a trained worker, or a grande worker on a summer action (or a year-round action) [1] OR place a winter worker, a trained worker, or a grande worker on a winter action (or a year-round action) [2]. 2. Pass [1][2]. If you pass during summer, you perform the following steps in order: 1. Move your rooster into the corresponding inner ring position on the wake-up chart (player order does not change) [3]. 2. Choose one of the depicted benefits (gain a grape token, draw any 1 card, or age 1 of your grape tokens) [3]. 3. Wait for all other players to pass [3]. 4. If you have a cottage, draw a visitor card [3].
🔧 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 237 ms · ask 7164 ms · total 7409 ms
- single-flight (PR-5)
- queued 0 ms · generation 7409 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.032266, "snippet": "In turn order (clockwise from the icon at the top of the track), choose one of the following two options: Place a summer worker, a trained worker, or a grande worker on a summer action (or a year-round action) OR pass. 1 . reveal a new event card spring Most actions are similar to those found on the", "headingPath": "summer", "sharpsignalDocId": 80}, {"page": 7, "score": 0.016393, "snippet": "When you pass during summer, you move into fall and perform the following steps in order: Move your rooster into the corresponding inner ring position on the wake-up chart (player order does not change). Choose one of the depicted benefits (gain , draw any 1 card, or age 1 of your grape tokens). The", "headingPath": "Fall", "sharpsignalDocId": 80}, {"page": 7, "score": 0.016129, "snippet": "In turn order, choose one of the following two options: Place a winter worker, a trained worker, or a grande worker on a winter action or a (or a year-round action) OR pass. 1 . reveal a new event card summer spring A B draw play Most actions are similar to those found on the core game board; howeve", "headingPath": "winter", "sharpsignalDocId": 80}, {"page": 7, "score": 0.015625, "snippet": "trade via grande worker (give once and/or take once) oval innovation tile bonus (only gained by trained workers, grande workers, and the temporary worker) win 25 10 win The year-end steps are largely the same as in core game, except that when each player passes during winter, they immediately perfor", "headingPath": "year end and Game end X 1 2 3 0 ? ", "sharpsignalDocId": 80}, {"page": 4, "score": 0.015385, "snippet": "During the spring season, perform the following 3 steps in order: Reveal 1 Event Card: Read the top card of the face-down event deck, starting with the historical flavor text and then the gameplay effect. Keep this card face-up next to the event deck. The gameplay effect only modifies the rules for ", "headingPath": "sprinG", "sharpsignalDocId": 80}, {"page": 1, "score": 0.015152, "snippet": "If a black-bordered card is drawn during a game of Viticulture World, discard it and redraw.", "headingPath": "VitiWorld_Punchboard_r8.indd 1 8/23/21 9:55 PM VitiWorld_Punchboard_r8.indd 1 pay (per tile) to gain up to two innovation tiles J play up to ; ; Compatibility and initial setup", "sharpsignalDocId": 80}, {"page": 4, "score": 0.014925, "snippet": "Cards in Hand: Each player's hand of cards (visitor, vine, wine order, structure) may be open or closed information, depending on your group's preferred play style. During cooperative play, the word 'opponent' on visitor or structure cards refers to your fellow players. Victory Point Track: Part of ", "headingPath": "General rules", "sharpsignalDocId": 80}, {"page": 3, "score": 0.014706, "snippet": "f Vineyard Mat: Each player takes a vineyard mat and places field cards on it as usual. Tokens: Each player places all tokens of their color next to their vineyard mat and performs the following: 1 1. 2 2. 3 3. Return 1 regular worker to the game box (leaving 4 regular workers and 1 grande worker). ", "headingPath": "Continent Difficulty Ranking:", "sharpsignalDocId": 80}]
- citations (raw)
- [{"page": 6, "quote": null, "headingPath": "summer", "sharpsignalDocId": 80}, {"page": 7, "quote": null, "headingPath": "winter", "sharpsignalDocId": 80}, {"page": 7, "quote": null, "headingPath": "Fall", "sharpsignalDocId": 80}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- 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
- Oct 30, 2026 02:26
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 World — Rulebook (corpus doc 80) | summer | p.6 | 0.032266 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | Fall | p.7 | 0.016393 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | winter | p.7 | 0.016129 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | year end and Game end X 1 2 3 0 ? | p.7 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #5 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | sprinG | p.4 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #6 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | VitiWorld_Punchboard_r8.indd 1 8/23/21 9:55 PM VitiWorld_Punchboard_r8.indd 1 pay (per tile) to gain up to two innovation tiles J play up to ; ; Compatibility and initial setup | p.1 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 92 |
| #7 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | General rules | p.4 | 0.014925 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | Continent Difficulty Ranking: | p.3 | 0.014706 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 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 World — Rulebook (corpus doc 80) | summer | p.6 | no quote on the wire |
| [2] | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | winter | p.7 | no quote on the wire |
| [3] | RULEBOOK Viticulture World — Rulebook (corpus doc 80) | Fall | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 237 ms · first delta n/a · total 7409 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 237 ms · ask 7164 ms · gateway work 7409 ms · total 7409 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 6s ago)
- stream path
- not recorded — this ruling predates the stream-path column (V41)
- 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 14), 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.