You asked
When does the game end?
Answered counted as answeredThe end of the game depends on the number of players and specific variants: 1. If there are two players in a bean duel, the game ends when the draw deck is exhausted for the first time [1]. 2. If there are three players, the game ends when the draw pile runs out for the second time [2]. 3. If there are four or more players, the game ends when the draw pile runs out for the third time [2], which can also occur during phase 2, 'Trading Bean Cards' [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 244 ms · ask 3628 ms · total 3881 ms
- single-flight (PR-5)
- queued 0 ms · generation 3881 ms
- retrieval refs (raw)
- [{"page": 7, "score": 0.032522, "snippet": "If there are three players, the game ends when the draw pile runs out for the second time . If there are four or more players, the game ends when the draw pile runs out for the third time, as usual.", "headingPath": "The End of the Game", "sharpsignalDocId": 79}, {"page": 6, "score": 0.032522, "snippet": "The game ends when the draw pile runs out for the third time. If this happens during phase 2, 'Trading Bean Cards' , complete phases 2 and 3 of your turn (even if you could only turn over one card instead of two), then the game ends. At the end of the game, harvest all of your bean fields and give y", "headingPath": "The end of The Game", "sharpsignalDocId": 79}, {"page": 8, "score": 0.031746, "snippet": "The bean duel with two players uses the same rules as the variant for three players with the following changes: Remove the Garden Beans and the Cocoa Beans from the game. A player may only sell beans from his bean fields on his turn. The game ends when the draw deck is exhausted for the first time. ", "headingPath": "The Bean duel for 2 players", "sharpsignalDocId": 79}, {"page": 3, "score": 0.03125, "snippet": "The starting player is the first active player. After that, players take turns going to the in clockwise order. The starting player keeps the starting player card for the whole game (see 'The End of the Game'). When it is your turn, you play through these four phases in order: Plant Bean Cards from ", "headingPath": "playInG The Game", "sharpsignalDocId": 79}, {"page": 7, "score": 0.030536, "snippet": "Play the game just like regular Bohnanza : Each player starts with five cards in their hands; On your turn, play through the usual four phases. Only the rules for phase 4, 'Drawing bean cards' , and the end of the game change when you play with extra types of beans.", "headingPath": "playInG The Game", "sharpsignalDocId": 79}, {"page": 8, "score": 0.015385, "snippet": "The active player draws the three topmost cards from the draw deck and puts them face up on the table so both players can see them. If the topmost card on the discard pile matches any of the cards just drawn, the player adds it to them. He does the same with the new topmost card from the discard pil", "headingPath": "3. Draw, plant, and offer beans", "sharpsignalDocId": 79}, {"page": 8, "score": 0.014925, "snippet": "After planting one or two cards in his bean fields (as in the normal game), the player may discard one card from anywhere in his hand face up on the discard pile.", "headingPath": "2. Plant bean cards & discard", "sharpsignalDocId": 79}, {"page": 7, "score": 0.014706, "snippet": "Unlike in the base game, every player draws one card from the draw pile , adding them to their hands behind the last card. Start with the active player and draw cards in a clockwise direction.", "headingPath": "Phase 4: Draw Bean Cards", "sharpsignalDocId": 79}]
- citations (raw)
- [{"page": 8, "quote": null, "headingPath": "The Bean duel for 2 players", "sharpsignalDocId": 79}, {"page": 7, "quote": null, "headingPath": "The End of the Game", "sharpsignalDocId": 79}, {"page": 6, "quote": null, "headingPath": "The end of The Game", "sharpsignalDocId": 79}]
- 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 02:24
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 Bohnanza — Rulebook (corpus doc 79) | The End of the Game | p.7 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 198 |
| #2 | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | The end of The Game | p.6 | 0.032522 (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 Bohnanza — Rulebook (corpus doc 79) | The Bean duel for 2 players | p.8 | 0.031746 (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 Bohnanza — Rulebook (corpus doc 79) | playInG The Game | p.3 | 0.03125 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #5 | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | playInG The Game | p.7 | 0.030536 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 266 |
| #6 | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | 3. Draw, plant, and offer beans | p.8 | 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 |
| #7 | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | 2. Plant bean cards & discard | p.8 | 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) | 162 |
| #8 | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | Phase 4: Draw Bean Cards | p.7 | 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) | 192 |
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 Bohnanza — Rulebook (corpus doc 79) | The Bean duel for 2 players | p.8 | no quote on the wire |
| [2] | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | The End of the Game | p.7 | no quote on the wire |
| [3] | RULEBOOK Bohnanza — Rulebook (corpus doc 79) | The end of The Game | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 244 ms · first delta n/a · total 3881 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 244 ms · ask 3628 ms · gateway work 3881 ms · total 3881 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 40s 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 13), 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.