You asked
Glazed Pavilion Expansion the base game (A) with the
Answered counted as answeredAsked with: Azul: Summer Pavilionbg-287954-en-1e · Azul: Summer Pavilion – Glazed Pavilionbg-332613-en-1e
🔧 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 101 ms · ask 3074 ms · total 3177 ms
- single-flight (PR-5)
- queued 0 ms · generation 3177 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 1, "score": 0.032787, "snippet": "On your turn, you must pick tiles. To do so you have two choices: OR Pick all tiles of the same color, which is not the wild color this round, from any one Factory display and place them next to your player board. Move the remaining tiles from this Factory display to the center of the table. Pick al", "headingPath": "Phase 1: Acquire Tiles", "sharpsignalDocId": 97}, {"page": 2, "score": 0.032002, "snippet": "This task is performed by the start player. If you have not yet reached round 6, advance the round counter on to the next round, in which you will start. If you are already in round 6, then move directly to the end of the game ( see next page ). Fill up the Factory displays with exactly 4 new tiles ", "headingPath": "Phase 3: Preparation for the Next Round", "sharpsignalDocId": 97}, {"page": 1, "score": 0.031498, "snippet": "The starting player begins. When it's your turn, first check that you have the right number of tiles in the needed color next to your player board to play in a space. If you have enough tiles, then place exactly one of these tiles on to the corresponding space of your player board. Discard the other", "headingPath": "Phase 2: Playing and Scoring Tiles", "sharpsignalDocId": 97}, {"page": 1, "score": 0.030777, "snippet": "A Each player chooses a player board (A) in one player color (as indicated by the colored circle between the red and orange stars) and places it in front of them, so that the side with the colored stars is face up. Place the Factory displays (B) in a circle around the center of the table: In a 2-pla", "headingPath": "GAME SETUP", "sharpsignalDocId": 97}, {"page": 1, "score": 0.03031, "snippet": "The player who has the start player token will be the first player to place their tiles on their board in Phase 2; and they will start the following round. This gives them the advantage of choosing tiles from the Factory displays first, according to the normal rules. After placing the tiles you have", "headingPath": "The start player token", "sharpsignalDocId": 97}, {"page": 2, "score": 0.029857, "snippet": "Andrea has 3 blue and 3 purple wild tiles next to her player board, which she can use to play on space '6' of her blue star. She places 1 blue tile onto her player board on space '6' and discards the 2 blue and 3 purple tiles into the tower. Andrea scores 3 points this turn because there are 2 other", "headingPath": "C", "sharpsignalDocId": 97}, {"page": 1, "score": 0.029418, "snippet": "Each round consists of the following phases: Phase 1: Acquire tiles Phase 2: Play tiles and score points Phase 3: Prepare the next round (this phase is not needed in the last round) The youngest player begins and play proceeds clockwise order. Several turns will be played per round.", "headingPath": "Gameplay", "sharpsignalDocId": 97}, {"page": 2, "score": 0.028992, "snippet": "For a slightly different play, all players turn their player board to the other side, showing the monochrome stars. The rules are identical to those of the normal game, with the following exceptions: During the game you , have the choice of which colors you place in the star shapes (for all 7 stars)", "headingPath": "Variant play", "sharpsignalDocId": 97}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 1, "quote": null, "headingPath": "Game Setup · Objective · Gameplay", "sharpsignalDocId": 909}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 97 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 97 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 0.89806 of 618 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 12, 2026 23:35
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: Summer Pavilion — Rulebook (corpus doc 97) | Phase 1: Acquire Tiles | p.1 | 0.032787 (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: Summer Pavilion — Rulebook (corpus doc 97) | Phase 3: Preparation for the Next Round | p.2 | 0.032002 (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: Summer Pavilion — Rulebook (corpus doc 97) | Phase 2: Playing and Scoring Tiles | p.1 | 0.031498 (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: Summer Pavilion — Rulebook (corpus doc 97) | GAME SETUP | p.1 | 0.030777 (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: Summer Pavilion — Rulebook (corpus doc 97) | The start player token | p.1 | 0.03031 (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 Azul: Summer Pavilion — Rulebook (corpus doc 97) | C | p.2 | 0.029857 (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 Azul: Summer Pavilion — Rulebook (corpus doc 97) | Gameplay | p.1 | 0.029418 (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)) | 283 |
| #8 | RULEBOOK Azul: Summer Pavilion — Rulebook (corpus doc 97) | Variant play | p.2 | 0.028992 (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 23 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 — 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: Summer Pavilion – Glazed Pavilion — Rulebook (corpus doc 909) | Game Setup · Objective · Gameplay | p.1 | #9 | 0.016129 (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 re-ranker chose it |
| #2 | RULEBOOK Azul: Summer Pavilion — Rulebook (corpus doc 97) | GAME SETUP | p.1 | #4 | 0.030777 (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: Summer Pavilion — Rulebook (corpus doc 97) | C | p.2 | #6 | 0.029857 (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: Summer Pavilion – Glazed Pavilion — Rulebook (corpus doc 909) | New Scoring Board · End of the Game · © 2021 Plan B Games Inc. | p.2 | #12 | 0.013889 (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: Summer Pavilion — Rulebook (corpus doc 97) | © 2019 Plan B Games Inc. | p.2 | #14 | 0.013514 (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 Azul: Summer Pavilion — Rulebook (corpus doc 97) | A | p.2 | #11 | 0.014085 (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 |
| #7 | RULEBOOK Azul: Summer Pavilion — Rulebook (corpus doc 97) | p.1 | #13 | 0.013699 (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 | |
| #8 | RULEBOOK Azul: Summer Pavilion – Glazed Pavilion — Rulebook (corpus doc 909) | New Player Boards | p.1 | #10 | 0.015385 (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 |
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: Summer Pavilion – Glazed Pavilion — Rulebook (corpus doc 909) | Game Setup · Objective · Gameplay | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 101 ms · first delta 1720 ms · total 3177 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 101 ms · ask 3074 ms · gateway work 3177 ms · total 3177 ms
- tokens in (the prompt the answerer read)
- 2379
- tokens out (what the answerer generated)
- 199
- tok/sec
- 140.1 tok/sec — 199 output tokens in 1.420 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 31s 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 28), 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.