You asked
How do I take my turn?
Answered counted as answeredAsked with: Azulbg-230802-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 266 ms · ask 4653 ms · total 4933 ms
- single-flight (PR-5)
- queued 0 ms · generation 4933 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.048916, "snippet": "On his turn, Peter picks the 2 black tiles from a Factory display and places the remaining tiles in the center of the table. Martin picks the yellow tile from a Factory display and places the remaining 3 red tiles in the center of the table. Then, Andrea picks these 3 red tiles from the center of th", "headingPath": "First turns example", "sharpsignalDocId": 95}, {"page": 3, "score": 0.048652, "snippet": "The starting player places the starting player marker in the center of the table and then takes the first turn. Play then continues clockwise. On your turn, you must pick tiles in one of the following ways: EITHER Pick all tiles of the same color from any one Factory display and then move the remain", "headingPath": "A. Factory offer", "sharpsignalDocId": 95}, {"page": 5, "score": 0.031746, "snippet": "If nobody has completed a horizontal line of 5 consecutive tiles on her wall yet (see End of the game), prepare the next round. The player with the starting player marker refills each of the Factory displays with 4 tiles from the bag as in the setup. If the bag is empty, refill it with all the tiles", "headingPath": "C. Preparing the next round", "sharpsignalDocId": 95}, {"page": 4, "score": 0.03125, "snippet": "This phase can be carried out by all players simultaneously, as they move tiles from their complete pattern lines over to their walls. Go through your pattern lines from top to bottom . Move the rightmost tile of each complete line to the space of the same color in the corresponding line of your wal", "headingPath": "B. Wall-tiling", "sharpsignalDocId": 95}, {"page": 4, "score": 0.030769, "snippet": "In all later rounds, you must also comply with the following rule: You are not allowed to place tiles of a certain color in a pattern line whose corresponding line of your wall already holds a tile of that color.", "headingPath": "First turns example", "sharpsignalDocId": 95}, {"page": 3, "score": 0.030303, "snippet": "The game is played over multiple rounds, each of which is composed of three phases: Factory offer Wall-tiling Preparing the next round", "headingPath": "Gameplay", "sharpsignalDocId": 95}, {"page": 5, "score": 0.029851, "snippet": "Each tile you move over to your wall is always placed on the space matching its color and immediately scores as follows: If there are no tiles directly adjacent (vertically or horizontally) to the newly placed tile, gain 1 point on the score track. If there are any tiles adjacent, however, do the fo", "headingPath": "Scoring", "sharpsignalDocId": 95}, {"page": 4, "score": 0.029412, "snippet": "Any tiles you have picked that you cannot or do not want to place according to the rules, you must place in your floor line , filling its spaces from left to right . These tiles are considered as having fallen on the floor and give minus points in the Wall-tiling phase. If all spaces of your floor l", "headingPath": "Floor line", "sharpsignalDocId": 95}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "A. Factory offer", "sharpsignalDocId": 95}, {"page": 4, "quote": null, "headingPath": "First turns example", "sharpsignalDocId": 95}, {"page": 4, "quote": null, "headingPath": "Floor line", "sharpsignalDocId": 95}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 95 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 95 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 9, 2026 23:48
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 Azul — Rulebook (corpus doc 95) | First turns example | p.3 | 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 Azul — Rulebook (corpus doc 95) | A. Factory offer | p.3 | 0.048652 (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 Azul — Rulebook (corpus doc 95) | C. Preparing the next round | p.5 | 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)) | 300 |
| #4 | RULEBOOK Azul — Rulebook (corpus doc 95) | B. Wall-tiling | p.4 | 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 Azul — Rulebook (corpus doc 95) | First turns example | p.4 | 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)) | 212 |
| #6 | RULEBOOK Azul — Rulebook (corpus doc 95) | Gameplay | p.3 | 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)) | 134 |
| #7 | RULEBOOK Azul — Rulebook (corpus doc 95) | Scoring | p.5 | 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 Azul — Rulebook (corpus doc 95) | Floor line | p.4 | 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.
candidate pool: the answering read scored 15 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 Azul — Rulebook (corpus doc 95) | A. Factory offer | p.3 | #2 | 0.048652 (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 Azul — Rulebook (corpus doc 95) | First turns example | p.4 | #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 Azul — Rulebook (corpus doc 95) | Floor line | p.4 | #8 | 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 Azul — Rulebook (corpus doc 95) | Game Setup | p.2 | #10 | 0.014286 (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 |
| #5 | RULEBOOK Azul — Rulebook (corpus doc 95) | Scoring | p.5 | #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 |
| #6 | RULEBOOK Azul — Rulebook (corpus doc 95) | C. Preparing the next round | p.5 | #3 | 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 |
| #7 | RULEBOOK Azul — Rulebook (corpus doc 95) | B. Wall-tiling | p.4 | #4 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Azul — Rulebook (corpus doc 95) | First turns example | p.3 | #1 | 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)) | 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 Azul — Rulebook (corpus doc 95) | A. Factory offer | p.3 | no quote on the wire |
| [2] | RULEBOOK Azul — Rulebook (corpus doc 95) | First turns example | p.4 | no quote on the wire |
| [3] | RULEBOOK Azul — Rulebook (corpus doc 95) | Floor line | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 266 ms · first delta 2960 ms · total 4933 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 266 ms · ask 4653 ms · gateway work 4933 ms · total 4933 ms
- tokens in (the prompt the answerer read)
- 2148
- tokens out (what the answerer generated)
- 270
- tok/sec
- 140.3 tok/sec — 270 output tokens in 1.924 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 53s 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 26), 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.