You asked
How do I take my turn?
Answered counted as answeredAsked with: Lancasterbg-96913-en-1e
🔧 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 232 ms · ask 11765 ms · total 12008 ms
- single-flight (PR-5)
- queued 0 ms · generation 12008 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 14, "score": 0.048916, "snippet": "'At the King's Court' affects the game play of phases 1 and 3. During phase 1, the players apply for the new offices of the country. During phase 3, the offices and privileges are distributed, which the players can use during the next game round. The active player places one of his own knights or hi", "headingPath": "Sequence of play modifications · Phase 1: Place knights or the lord · The lord applies for an office · The lord enters the treasury", "sharpsignalDocId": 139}, {"page": 2, "score": 0.048139, "snippet": "Randomly determine a start player, give them the start player marker. The players take their turns in clockwise direction. The game is played over five game rounds. Each round consists of 3 Phases: 1: Place knights 2: Parliament 3: Rewards The active player takes one of their own knights from their ", "headingPath": "Sequence of play · Phase 1: Place knights · County", "sharpsignalDocId": 139}, {"page": 11, "score": 0.032258, "snippet": "Please see the detailed description of the new laws on the back of this rules sheet. The new laws may enter the game in 2 different ways : Replace all law cards of the basic game with the new law cards. Leave the old laws in the box, they are not used for this game. You may combine the old and new l", "headingPath": "· 18 new law cards · PARLIAMENT · 1st option 'The game with the new laws' · 2nd option 'The game with variable combinations' · Nobleman tiles", "sharpsignalDocId": 139}, {"page": 12, "score": 0.03125, "snippet": "Players have to flip each extension for which they do not want to pay this charge or cannot do so. Players decide in player order, beginning with the start player. These extensions are flipped back after scoring all castles. Players gain 3 power points for every 2 squires supporting their own knight", "headingPath": "Players must return 1 squire to the general supply for each existing extension of their castle.", "sharpsignalDocId": 139}, {"page": 6, "score": 0.030769, "snippet": "Reveal 3 new laws from the top of the draw pile, one after the other, and place them on the 3 spaces for new laws, from left to right. Please note: Knights in the reserve area do not belong to the knighthood. Hint: If a there is still a draw for the first position after considering the number of squ", "headingPath": "Parliament:", "sharpsignalDocId": 139}, {"page": 18, "score": 0.030303, "snippet": "Prior to evaluating the counties, the tower is cleared and the knights go back to their owners' court. The knight of the non-player color remains inside the tower. For each lost conflict, the players who contributed no knights to that conflict receive dishonor markers. All affected players receive 1", "headingPath": "Counties · Conflicts · Final scoring · Special rules for a 2 player game", "sharpsignalDocId": 139}, {"page": 3, "score": 0.029851, "snippet": "The player places their knight on an empty knight's space in their own castle. Each space can hold only one knight. A player may engage in as many conflicts as they wish. The player selects a conflict and places their knight on the topmost empty knight's space. Each player may occupy only one of the", "headingPath": "Castle · Conflict · Immediate reward: · Phase 2: Parliament · Voting procedure · Voting result · …", "sharpsignalDocId": 139}, {"page": 17, "score": 0.029412, "snippet": "As of now, there is one more location where the players can place their knights: The tower. The tower can contain knights with a total strength of 7. The active player may drop 1 of his knights inside the tower; then, he disposes of 1 dishonor marker for each strength point of the knight he dropped ", "headingPath": "Phase 1: Place knights", "sharpsignalDocId": 139}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "Sequence of play · Phase 1: Place knights · County", "sharpsignalDocId": 139}, {"page": 14, "quote": null, "headingPath": "Sequence of play modifications · Phase 1: Place knights or the lord · The lord applies for an office · The lord enters the treasury", "sharpsignalDocId": 139}, {"page": 3, "quote": null, "headingPath": "Castle · Conflict · Immediate reward: · Phase 2: Parliament · Voting procedure · Voting result · …", "sharpsignalDocId": 139}, {"page": 4, "quote": null, "headingPath": "The new law is approved · The new law is rejected · Use the same procedure for voting on the 2nd and 3rd new law. · Implementation of the 3 applicable laws · Phase 3: Rewards · Counties · …", "sharpsignalDocId": 139}, {"page": 5, "quote": null, "headingPath": "Castles · Conflicts · 1. Winner of conflict: England or France · Assigning power points: · Example:", "sharpsignalDocId": 139}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 139 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 139 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 6, 2026 14:41
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. How much wider that pool was is set gateway-side and is NOT REPORTED for this ruling, and neither are the answerer's final rows — so rulesage has nothing of its own to show beside these.
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 Lancaster — Rulebook (corpus doc 139) | Sequence of play modifications · Phase 1: Place knights or the lord · The lord applies for an office · The lord enters the treasury | p.14 | 0.048916 (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 Lancaster — Rulebook (corpus doc 139) | Sequence of play · Phase 1: Place knights · County | p.2 | 0.048139 (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 Lancaster — Rulebook (corpus doc 139) | · 18 new law cards · PARLIAMENT · 1st option 'The game with the new laws' · 2nd option 'The game with variable combinations' · Nobleman tiles | p.11 | 0.032258 (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 Lancaster — Rulebook (corpus doc 139) | Players must return 1 squire to the general supply for each existing extension of their castle. | p.12 | 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)) | 300 |
| #5 | RULEBOOK Lancaster — Rulebook (corpus doc 139) | Parliament: | p.6 | 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 Lancaster — Rulebook (corpus doc 139) | Counties · Conflicts · Final scoring · Special rules for a 2 player game | p.18 | 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 Lancaster — Rulebook (corpus doc 139) | Castle · Conflict · Immediate reward: · Phase 2: Parliament · Voting procedure · Voting result · … | p.3 | 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 Lancaster — Rulebook (corpus doc 139) | Phase 1: Place knights | p.17 | 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)) | 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.
the passages the answerer read: NOT RECORDED for this ruling. Any of three things leaves this empty, and they are all different from the answerer having had nothing to read: this ask may never have reached a gateway at all; a multi-book ask keeps each book's own context on that book's own page rather than here; or the gateway build that answered may simply not report it. What this NEVER means is that the answerer read nothing — an answer was composed from passages either way, and their absence here is a gap in what we were told, not in what it read.
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 Lancaster — Rulebook (corpus doc 139) | Sequence of play · Phase 1: Place knights · County | p.2 | no quote on the wire |
| [2] | RULEBOOK Lancaster — Rulebook (corpus doc 139) | Sequence of play modifications · Phase 1: Place knights or the lord · The lord applies for an office · The lord enters the treasury | p.14 | no quote on the wire |
| [3] | RULEBOOK Lancaster — Rulebook (corpus doc 139) | Castle · Conflict · Immediate reward: · Phase 2: Parliament · Voting procedure · Voting result · … | p.3 | no quote on the wire |
| [4] | RULEBOOK Lancaster — Rulebook (corpus doc 139) | The new law is approved · The new law is rejected · Use the same procedure for voting on the 2nd and 3rd new law. · Implementation of the 3 applicable laws · Phase 3: Rewards · Counties · … | p.4 | no quote on the wire |
| [5] | RULEBOOK Lancaster — Rulebook (corpus doc 139) | Castles · Conflicts · 1. Winner of conflict: England or France · Assigning power points: · Example: | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 232 ms · first delta 7388 ms · total 12008 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 232 ms · ask 11765 ms · gateway work 12008 ms · total 12008 ms
- tokens in (the prompt the answerer read)
- 4307
- tokens out (what the answerer generated)
- 617
- tok/sec
- 135.1 tok/sec — 617 output tokens in 4.568 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 20s 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 61), 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.