You asked
How do I take my turn?
Answered counted as answeredOn your turn, you must follow these steps: 1. Choose a different section of your Player Mat than the one used during your previous turn [1][2]. (Note: The Rusviet faction may choose the same section as the previous turn) [3]. 2. Place your action token on that section [1]. 3. Pay the full cost of the action (all icons on exposed red boxes) before gaining the benefit (exposed green boxes) [1][2]. 4. Take the top-row action, the bottom-row action, or both (starting with the top action) [1][2]. 5. If you choose to take a bottom-row action, you may take the coins before implementing the main focus of the action so you do not forget them [4][2]. 6. You may also reveal a completed objective card during your turn, either before or after completing a top- or bottom-row action [1][5].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:12b think:false 4eb23ef187e2
- timings
- search 200 ms · ask 10833 ms · total 11044 ms
- single-flight (PR-5)
- queued 0 ms · generation 11044 ms
- retrieval refs (raw)
- [{"page": 10, "score": 0.032787, "snippet": "Scythe uses an ongoing action-selection mechanism (no rounds or phases). Players take turns one after another until a player places their 6th star on the board, immediately ending the game. On your turn, do the following in sequential order: Place your action token on a different section of your Pla", "headingPath": "GAMEPLAY", "sharpsignalDocId": 44}, {"page": 14, "score": 0.032002, "snippet": "The bottom-row actions are in the same order on all Player Mats, but the costs and benefits vary. The Player Mat visuals and the default costs and benefits explained in this section are based on the starting position of each Player Mat. OVERLAPPING TURNS: Usually when a player starts to take the bot", "headingPath": "BOTTOM-ROW ACTIONS", "sharpsignalDocId": 44}, {"page": 31, "score": 0.031281, "snippet": "RESOURCES: All units-characters, mechs, & workers-can carry around resources (any number). TURNS AND PLAYER MATS: On your turn, you must choose a different section of your Player Mat than you did the previous turn. Take either the top-row action, the bottom-row action, or both (starting with the top", "headingPath": "HIGHLIGHTED RULES", "sharpsignalDocId": 44}, {"page": 24, "score": 0.029631, "snippet": "As your character treks across Eastern Europa, they will encounter a number of local people and situations. Each encounter will present you with three options to determine how you want to interact with the people. The choice you make will often impact the peoples' view of you, represented in the gam", "headingPath": "ENCOUNTERS", "sharpsignalDocId": 44}, {"page": 28, "score": 0.029236, "snippet": "If the 6th star comes from taking a bottom-row action, gain the primary benefit, the coins, and the Recruit Ongoing Benefit before placing the star. If you have units (character, mechs, or workers) remaining on a territory with an opponent's units (from a Move action), you must undo that portion of ", "headingPath": "EDGE CASES", "sharpsignalDocId": 44}, {"page": 25, "score": 0.028259, "snippet": "Each Factory card is the equivalent of a fifth section of your Player Mat (place it next to your Player Mat). USING FACTORY ACTIONS: The Factory card is treated as any other section on your Player Mat. On your turn, you may place your action token on the Factory card and take one or both actions (st", "headingPath": "FACTORY CARDS", "sharpsignalDocId": 44}, {"page": 23, "score": 0.027984, "snippet": "Both players reveal their Power Dials and selected combat cards simultaneously. The value provided by any combat cards provides an additional bonus to the power you spend from the Power Track as indicated on your Power Dial. The player with the highest total power wins the combat (ties go to the att", "headingPath": "REVEAL", "sharpsignalDocId": 44}, {"page": 21, "score": 0.027149, "snippet": "Each faction has a special ability indicated at the upper right of the Faction Mat. RUSVIET (RELENTLESS): You may choose the same section on your Player Mat as the previous turn(s). The Rusviets push their people hard, day after day, to achieve their ultimate goal. While other factions let their inf", "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 44}]
- citations (raw)
- [{"page": 10, "quote": null, "headingPath": "GAMEPLAY", "sharpsignalDocId": 44}, {"page": 31, "quote": null, "headingPath": "HIGHLIGHTED RULES", "sharpsignalDocId": 44}, {"page": 21, "quote": null, "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 44}, {"page": 14, "quote": null, "headingPath": "BOTTOM-ROW ACTIONS", "sharpsignalDocId": 44}, {"page": 26, "quote": null, "headingPath": "O B J E C T I V E S", "sharpsignalDocId": 44}]
- 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 22, 2026 01:13
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 Scythe — Rulebook (corpus doc 44) | GAMEPLAY | p.10 | 0.032787 (at the 2-arm ceiling (0.03279) — the top of a 2-arm fuse; whether more arms ran here was never recorded) | 300 |
| #2 | RULEBOOK Scythe — Rulebook (corpus doc 44) | BOTTOM-ROW ACTIONS | p.14 | 0.032002 (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 Scythe — Rulebook (corpus doc 44) | HIGHLIGHTED RULES | p.31 | 0.031281 (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 Scythe — Rulebook (corpus doc 44) | ENCOUNTERS | p.24 | 0.029631 (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 Scythe — Rulebook (corpus doc 44) | EDGE CASES | p.28 | 0.029236 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #6 | RULEBOOK Scythe — Rulebook (corpus doc 44) | FACTORY CARDS | p.25 | 0.028259 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #7 | RULEBOOK Scythe — Rulebook (corpus doc 44) | REVEAL | p.23 | 0.027984 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #8 | RULEBOOK Scythe — Rulebook (corpus doc 44) | F A C T I O N A B I L I T I E S | p.21 | 0.027149 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; 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 Scythe — Rulebook (corpus doc 44) | GAMEPLAY | p.10 | no quote on the wire |
| [2] | RULEBOOK Scythe — Rulebook (corpus doc 44) | HIGHLIGHTED RULES | p.31 | no quote on the wire |
| [3] | RULEBOOK Scythe — Rulebook (corpus doc 44) | F A C T I O N A B I L I T I E S | p.21 | no quote on the wire |
| [4] | RULEBOOK Scythe — Rulebook (corpus doc 44) | BOTTOM-ROW ACTIONS | p.14 | no quote on the wire |
| [5] | RULEBOOK Scythe — Rulebook (corpus doc 44) | O B J E C T I V E S | p.26 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 200 ms · first delta n/a · total 11044 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 200 ms · ask 10833 ms · gateway work 11044 ms · total 11044 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 39s 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 2), 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.