You asked
How do I play?
Answered counted as answeredAsked with: Windmill Valleybg-403441-en-1e
The book has spoken.
🔧 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 83 ms · ask 6256 ms · total 11035 ms
- single-flight (PR-5)
- queued 4694 ms · generation 6341 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048412, "snippet": "In Windmill Valley , players continuously take turns until one player reaches the end of the Calendar track, triggering the end of the game. When this happens, finish the current round, so all players get the same number of turns. Then, everyone plays one more turn and moves on to the final scoring.", "headingPath": "Missing or damaged components :", "sharpsignalDocId": 705}, {"page": 5, "score": 0.048131, "snippet": "8 In reverse turn order , each player must place one of their Player markers on an area of the market which does not contain another player marker, if possible. Then: 9 In a 2-player game, place one neutral marker in each of the three areas of the Market. In a 3-player game, place one neutral marker", "headingPath": "Missing or damaged components :", "sharpsignalDocId": 705}, {"page": 12, "score": 0.047379, "snippet": "Score a number of Victory Points for each complete row and each complete column of Patches based on the colors of their Tulip Bulbs: Each row of Patches has two different Victory Point values. A complete row of Patches scores the higher number of Victory Points if all the Tulip Bulbs share the same ", "headingPath": "Scoring Patches · Final Score and Breaking Ties", "sharpsignalDocId": 705}, {"page": 4, "score": 0.031746, "snippet": "2 Place the Main board on the table. 1 Place the 'X' tiles, the Wheel Enhancements, Farm Enhancements cards, Tulip Bulbs and Tool tokens near the board and within easy reach of all players. 2 3", "headingPath": "Missing or damaged components :", "sharpsignalDocId": 705}, {"page": 10, "score": 0.030769, "snippet": "This action allows you to move your player marker on the Market area of the Main board in order to gain various rewards. Whenever you perform this action, resolve it according to numbers depicted on its icon. The red number is the cost-how many Guilder you must spend in order to perform this action.", "headingPath": "Action: Visit the Market · Market Movement", "sharpsignalDocId": 705}, {"page": 5, "score": 0.030303, "snippet": "Shuffle each type of Wheel Enhancement tiles separately forming stacks, and place them next to the Main board. Then, draw two Common Enhancements, one Uncommon Enhancement, and one Unique Enhancement and place them in their respective spaces on the Main board (3A). 3 A setup example for 3 players Sh", "headingPath": "Missing or damaged components :", "sharpsignalDocId": 705}, {"page": 8, "score": 0.029851, "snippet": "Whenever the red spoke on the Large Wheel aligns with, or crosses the red arrow on your Windmill board, you must move your player marker one step to the right on the Calendar track. At any point during your current turn, you may receive the common reward, as well as select one of the available uniqu", "headingPath": "Calendar", "sharpsignalDocId": 705}, {"page": 3, "score": 0.029727, "snippet": "Tools and Tulip Bulbs are not meant to be limited. If at any point you run out of any of these components, use any suitable replacements to represent them. Before your first game, carefully punch out all cardboard components, and separate all other elements, as it will make setting up the game much ", "headingPath": "LIVING RULES PLEDGE · Missing or damaged components :", "sharpsignalDocId": 705}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "Missing or damaged components :", "sharpsignalDocId": 705}, {"page": 10, "quote": null, "headingPath": "Action: Visit the Market · Market Movement", "sharpsignalDocId": 705}, {"page": 11, "quote": null, "headingPath": "Market Movement", "sharpsignalDocId": 705}, {"page": 10, "quote": null, "headingPath": "Action: Build a Windmill", "sharpsignalDocId": 705}, {"page": 8, "quote": null, "headingPath": "Calendar", "sharpsignalDocId": 705}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 705 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 705 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 0.93813 of 1778 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 22, 2026 19:19 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 Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.6 | 0.048412 (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 Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.5 | 0.048131 (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 Windmill Valley — Rulebook (corpus doc 705) | Scoring Patches · Final Score and Breaking Ties | p.12 | 0.047379 (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 Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.4 | 0.031746 (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)) | 193 |
| #5 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Action: Visit the Market · Market Movement | p.10 | 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 |
| #6 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.5 | 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 Windmill Valley — Rulebook (corpus doc 705) | Calendar | p.8 | 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 Windmill Valley — Rulebook (corpus doc 705) | LIVING RULES PLEDGE · Missing or damaged components : | p.3 | 0.029727 (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 33 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 Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.5 | #2 | 0.048131 (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 Windmill Valley — Rulebook (corpus doc 705) | Action: Visit the Market · Market Movement | p.10 | #5 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Action: Build a Windmill | p.10 | #9 | 0.029412 (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 |
| #4 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Calendar | p.8 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Market Movement | p.11 | #20 | 0.0125 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.5 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.4 | #4 | 0.031746 (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 |
| #8 | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.6 | #1 | 0.048412 (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 Windmill Valley — Rulebook (corpus doc 705) | Missing or damaged components : | p.6 | no quote on the wire |
| [2] | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Action: Visit the Market · Market Movement | p.10 | no quote on the wire |
| [3] | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Market Movement | p.11 | no quote on the wire |
| [4] | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Action: Build a Windmill | p.10 | no quote on the wire |
| [5] | RULEBOOK Windmill Valley — Rulebook (corpus doc 705) | Calendar | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 83 ms · first delta 2647 ms · total 11035 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 4694 ms · retrieval 83 ms · ask 6256 ms · gateway work 6341 ms · total 11035 ms
- tokens in (the prompt the answerer read)
- 3314
- tokens out (what the answerer generated)
- 479
- tok/sec
- 132.8 tok/sec — 479 output tokens in 3.607 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, checked 2s 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 638), 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.