You asked
How do I take my turn?
Answered counted as answeredAsked with: Messina 1347bg-238799-en-1e
That's the page. Back to the table.
🔧 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 105 ms · ask 2944 ms · total 3053 ms
- single-flight (PR-5)
- queued 0 ms · generation 3053 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 14, "score": 0.047883, "snippet": "If you get an advance on a register during production, move your counter immediately. However, if this advance leads to an action, you do not take the action until the Action step of your next turn. (And if this happens at the end of the final round, you will not take the action at all.)", "headingPath": "ADVANCING DURING PRODUCTION", "sharpsignalDocId": 764}, {"page": 15, "score": 0.047123, "snippet": "Yellow wants to take a Build action. He decides to move the lieutenant shown above. Movement to the adjacent hex is free, but the additional move costs 1 coin. Note that Red's figure is lying down and therefore is not blocking the hex. Yellow will stand his figure on the chosen hex, indicating that ", "headingPath": "EXAMPLE TURN", "sharpsignalDocId": 764}, {"page": 10, "score": 0.046898, "snippet": "The hex you choose allows you to take one specific action. Some actions have simple consequences, such as gaining a fire token. Some actions lead to other actions, which offer many interesting opportunities to build your reputation. To perform these actions, simply take the indicated tokens. There i", "headingPath": "Actions · Actions with Options · Advance on Register · Advance on Your Scroll Board · OVERSEER'S PATH", "sharpsignalDocId": 764}, {"page": 6, "score": 0.046432, "snippet": "Each player chooses a color. Take the player board, the figures, the cubes, the counters, and the overseer tokens in your color. You also take a scroll board, which fits beside your player board as shown below. Keep 3 of your figures near your board for now. You will send them to Messina on your fir", "headingPath": "Player Setup · Play Order · ADVANCED GAME SETUP", "sharpsignalDocId": 764}, {"page": 9, "score": 0.045475, "snippet": "On your turn, you can send your lieutenant to choose a boat instead of a hex. The steps are similar to a regular turn: Choose a boat in Messina and move your lieutenant to its dock, according to the usual movement rules. (Count the dock as a separate hex adjacent to the harbor.) You may even go to a", "headingPath": "Choosing a Boat · DOCKS VERSUS HEXES", "sharpsignalDocId": 764}, {"page": 8, "score": 0.032787, "snippet": "In Rounds II-VI: You already have lieutenants in Messina, on the hexes they occupied in the previous round. They begin the new round lying down to show they have not been used and are not blocking that hex. When choosing a hex for a lying-down figure, you can choose the same hex or an adjacent hex f", "headingPath": "Your turn", "sharpsignalDocId": 764}, {"page": 7, "score": 0.030886, "snippet": "You are now ready to add boats, plague cubes, and citizens to Messina. In round I, 1 boat arrives: Draw the top docking tile from its stack to determine which dock gets the boat. Place the top boat tile in one of the dock's spaces, face up. Give that boat tile 1 plague cube. Now the plague spreads t", "headingPath": "Round I Setup · A Boat Docks · Population Wheel · Gameplay · Your turn", "sharpsignalDocId": 764}, {"page": 16, "score": 0.029851, "snippet": "Advance the round counter to the next round. Lay all lieutenant figures in Messina flat on their hexes to show that they have not been used yet in the new round. Remove citizen tokens from hexes that have plague cubes. Check the round info table to see which register has priority this round. Rearran", "headingPath": "Setup for Next Round", "sharpsignalDocId": 764}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 7, "quote": null, "headingPath": "Round I Setup · A Boat Docks · Population Wheel · Gameplay · Your turn", "sharpsignalDocId": 764}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 764 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 764 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 0.91042 of 547 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 15, 2026 15:35 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 Messina 1347 — Rulebook (corpus doc 764) | ADVANCING DURING PRODUCTION | p.14 | 0.047883 (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)) | 288 |
| #2 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | EXAMPLE TURN | p.15 | 0.047123 (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 Messina 1347 — Rulebook (corpus doc 764) | Actions · Actions with Options · Advance on Register · Advance on Your Scroll Board · OVERSEER'S PATH | p.10 | 0.046898 (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 Messina 1347 — Rulebook (corpus doc 764) | Player Setup · Play Order · ADVANCED GAME SETUP | p.6 | 0.046432 (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 Messina 1347 — Rulebook (corpus doc 764) | Choosing a Boat · DOCKS VERSUS HEXES | p.9 | 0.045475 (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 Messina 1347 — Rulebook (corpus doc 764) | Your turn | p.8 | 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 |
| #7 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | Round I Setup · A Boat Docks · Population Wheel · Gameplay · Your turn | p.7 | 0.030886 (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 Messina 1347 — Rulebook (corpus doc 764) | Setup for Next Round | p.16 | 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 |
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 35 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 Messina 1347 — Rulebook (corpus doc 764) | ADVANCING DURING PRODUCTION | p.14 | #1 | 0.047883 (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 Messina 1347 — Rulebook (corpus doc 764) | Player Setup · Play Order · ADVANCED GAME SETUP | p.6 | #4 | 0.046432 (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 |
| #3 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | Your turn | p.8 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | Registers · Advancing · Types of Actions | p.14 | #9 | 0.029469 (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 re-ranker chose it |
| #5 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | 2. Rescuing a Citizen | p.8 | #19 | 0.012987 (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 Messina 1347 — Rulebook (corpus doc 764) | EXAMPLE TURN | p.15 | #2 | 0.047123 (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 |
| #7 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | Round I Setup · A Boat Docks · Population Wheel · Gameplay · Your turn | p.7 | #7 | 0.030886 (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 re-ranker chose it |
| #8 | RULEBOOK Messina 1347 — Rulebook (corpus doc 764) | Choosing a Boat · DOCKS VERSUS HEXES | p.9 | #5 | 0.045475 (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 Messina 1347 — Rulebook (corpus doc 764) | Round I Setup · A Boat Docks · Population Wheel · Gameplay · Your turn | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 105 ms · first delta 2132 ms · total 3053 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 105 ms · ask 2944 ms · gateway work 3053 ms · total 3053 ms
- tokens in (the prompt the answerer read)
- 3404
- tokens out (what the answerer generated)
- 167
- tok/sec
- 202.2 tok/sec — 167 output tokens in 0.826 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 49s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 9s 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 698), 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.