You asked
How do I take my turn?
Answered counted as answeredAsked with: Dune: Imperiumbg-316554-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 108 ms · ask 3915 ms · total 4024 ms
- single-flight (PR-5)
- queued 0 ms · generation 4024 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 8, "score": 0.04918, "snippet": "Starting with the player who has the First Player marker and continuing clockwise, players take one turn at a time. On your turn, you will take either an Agent turn or a Reveal turn . These types of turns are detailed over the next three pages. Generally, you will take Agent turns until you run out ", "headingPath": "phAse 2: plAyer turns", "sharpsignalDocId": 87}, {"page": 19, "score": 0.046394, "snippet": "After each of the First Player's Agent turns, House Hagal acts, as long as it has an Agent remaining in its supply. (Use the method described earlier) The number of turns that House Hagal takes each round will vary because it acts after the First Player. For example, if one player has a Swordmaster ", "headingPath": "durInG the GAme", "sharpsignalDocId": 87}, {"page": 20, "score": 0.045285, "snippet": "During Phase 2: Player Turns, your Rivals each take Agent turns in sequence with you, as long as they have an Agent remaining in their supply. (Use the method described earlier.) When a Rival uses Harvest Spice to send an Agent to a board space, it gains all spice there (base and bonus). Place any a", "headingPath": "rIvAls' turns", "sharpsignalDocId": 87}, {"page": 11, "score": 0.045009, "snippet": "When a player has no more Agents for Agent turns (or chooses not to use any Agents they have remaining), that player takes a Reveal turn. This consists of the following steps in order: Reveal Cards, Resolve Reveal Effects, Set Strength, and Clean Up.", "headingPath": "Harvesting Spice", "sharpsignalDocId": 87}, {"page": 13, "score": 0.044776, "snippet": "Baron Vladimir Harkonnen To use the Masterstroke ability, choose two of the four Baron Harkonnen tokens and place them on your Leader with the Faction side face down. (Return the other two to the box without letting any opponents see them.) Later, reveal your choices as described to gain your reward", "headingPath": "clArIFIcAtIons", "sharpsignalDocId": 87}, {"page": 9, "score": 0.032258, "snippet": "In an Agent turn, you play one card from your hand face up in front of you, using it to send an Agent from your Leader to an unoccupied space on the game board. This board space must have an icon in its upper left corner matching one of the Agent icons on the card. You must choose only one Agent ico", "headingPath": "plAyer turn - AGent turn", "sharpsignalDocId": 87}, {"page": 11, "score": 0.031746, "snippet": "Remove all the cards from in front of you (from your Agent and Reveal turns) and put them in your discard pile.", "headingPath": "cleAn up", "sharpsignalDocId": 87}, {"page": 8, "score": 0.03125, "snippet": "Each round begins by revealing a new Conflict card from the top of the Conflict Deck. Place it face up in the space next to the Conflict Deck (on top of any Conflict cards from previous rounds). Next, each player draws five cards from their own deck, forming their hand for the round.", "headingPath": "phAse 1: round stArt", "sharpsignalDocId": 87}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 8, "quote": null, "headingPath": "phAse 2: plAyer turns", "sharpsignalDocId": 87}, {"page": 9, "quote": null, "headingPath": "plAyer turn - AGent turn", "sharpsignalDocId": 87}, {"page": 11, "quote": null, "headingPath": "Harvesting Spice", "sharpsignalDocId": 87}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 87 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 87 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 0.91432 of 852 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 05:53
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 Dune: Imperium — Rulebook (corpus doc 87) | phAse 2: plAyer turns | p.8 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | durInG the GAme | p.19 | 0.046394 (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 Dune: Imperium — Rulebook (corpus doc 87) | rIvAls' turns | p.20 | 0.045285 (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 Dune: Imperium — Rulebook (corpus doc 87) | Harvesting Spice | p.11 | 0.045009 (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)) | 250 |
| #5 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | clArIFIcAtIons | p.13 | 0.044776 (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 Dune: Imperium — Rulebook (corpus doc 87) | plAyer turn - AGent turn | p.9 | 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 |
| #7 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | cleAn up | p.11 | 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)) | 111 |
| #8 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | phAse 1: round stArt | p.8 | 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)) | 284 |
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 80 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 Dune: Imperium — Rulebook (corpus doc 87) | phAse 2: plAyer turns | p.8 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | clArIFIcAtIons | p.13 | #5 | 0.044776 (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 Dune: Imperium — Rulebook (corpus doc 87) | Harvesting Spice | p.11 | #4 | 0.045009 (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 |
| #4 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | rIvAls' turns | p.20 | #3 | 0.045285 (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 |
| #5 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | set strenGth | p.11 | #36 | 0.010989 (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 Dune: Imperium — Rulebook (corpus doc 87) | Icon GuIde And AddItIonAl terms | p.16 | #10 | 0.028043 (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 |
| #7 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | plAyer turn - AGent turn | p.9 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | Mentat | p.18 | #13 | 0.025038 (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 |
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 Dune: Imperium — Rulebook (corpus doc 87) | phAse 2: plAyer turns | p.8 | no quote on the wire |
| [2] | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | plAyer turn - AGent turn | p.9 | no quote on the wire |
| [3] | RULEBOOK Dune: Imperium — Rulebook (corpus doc 87) | Harvesting Spice | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 108 ms · first delta 2725 ms · total 4024 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 108 ms · ask 3915 ms · gateway work 4024 ms · total 4024 ms
- tokens in (the prompt the answerer read)
- 1756
- tokens out (what the answerer generated)
- 263
- tok/sec
- 207.4 tok/sec — 263 output tokens in 1.268 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 38s 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 18), 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.