You asked
How do I take my turn?
Answered counted as answeredAsked with: Septimabg-360692-en-1e
The book has spoken.
🔧 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 85 ms · ask 5318 ms · total 5404 ms
- single-flight (PR-5)
- queued 0 ms · generation 5404 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 7, "score": 0.04918, "snippet": "4 The Covens execute their plans. All players resolve their chosen Action in turn order. When you take your turn, fully resolve the following steps in order. 5 1 QUICK MOVE: You may optionally move 1 space with your Leader (see the Move Action card description for rules on moving). When performing t", "headingPath": "RESOLVE ACTION", "sharpsignalDocId": 1120}, {"page": 9, "score": 0.045956, "snippet": "4 4 4 4 4 5 A player may gain a Spell of a specific element whenever they advance onto a space on a ribbon showing the gain Spell icon. The Spells available for the player depend on the section the Ritual marker is in. If the marker is on a space inside of a section, only a Spell of the correspondin", "headingPath": "SPELLS", "sharpsignalDocId": 1120}, {"page": 10, "score": 0.045445, "snippet": "You must, in turn order, check if you have raised your Suspicion at any point during this Moon Phase. If you have not, skip this step. 1 6 1 6 If you did raise your Suspicion during this Moon Phase, you must first check if an Active Hunter (standing upright) resides in a Hut in the same Zone as your", "headingPath": "HUNTER ROLL", "sharpsignalDocId": 1120}, {"page": 6, "score": 0.043935, "snippet": "? 4 3 3 4 There are five identical Moon Phases in each Season. Each Moon Phase consists of five steps (labeled A -E ). All players fully resolve each step before moving on to the next. Most of these steps must be resolved in turn order, while others may be resolved simultaneously. Use the Turn Step ", "headingPath": "5 MOON PHASES · 3x 4x 5 6 A SELECT ACTION · Player board", "sharpsignalDocId": 1120}, {"page": 5, "score": 0.032258, "snippet": "VI Shuffle the remaining Witch tiles together, and place them face down on top of the Witch tile stack. 8 Take a Player Aid. It shows Potion recipes on one side (keep that side up for now) and a summary of the gameplay steps on the other side. 9 Draw 2 Prologue cards to determine your starting asset", "headingPath": "PLAYER SETUP", "sharpsignalDocId": 1120}, {"page": 5, "score": 0.030769, "snippet": "I V Each player should choose an available player color and take the following steps. 1 Take into your hand all 9 Action cards of your color. II III IV 2x 2 Take a Player board. If you'll be playing a Full Game, use he side of the Player board that shows the Full Game symbol in the top right corner.", "headingPath": "PLAYER SETUP", "sharpsignalDocId": 1120}, {"page": 14, "score": 0.030303, "snippet": "When you select your Action, you may choose to play a Negotiation card alongside it to affect what Action card the Black Widow will select. You have 4 options for Negotiation cards. 1 PLAY NO NEGOTIATION: Select your Action card, then roll the Solo die to see which one of the Black Widow's Action ca", "headingPath": "SELECT ACTION", "sharpsignalDocId": 1120}, {"page": 6, "score": 0.029469, "snippet": "PROLOGUE CARD EXAMPLE: You choose to place the top card over the bottom so that the lower half of the top card covers the higher half of the bottom. You then choose three times whether to gain a Berry or an Herb, and gain 2 Crystals and 1 Flying Ointment. 10 The player who last made a mixed drink wi", "headingPath": "PLAYER SETUP · FULL GAME · 6 SEASON SEQUENCE", "sharpsignalDocId": 1120}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 7, "quote": null, "headingPath": "RESOLVE ACTION", "sharpsignalDocId": 1120}, {"page": 14, "quote": null, "headingPath": "RESOLVE ACTION · BLACK WIDOW'S SUSPICION", "sharpsignalDocId": 1120}, {"page": 9, "quote": null, "headingPath": "SPELLS", "sharpsignalDocId": 1120}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1120 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1120 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 0.91696 of 1445 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 26, 2026 08:42 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 Septima — Rulebook (corpus doc 1120) | RESOLVE ACTION | p.7 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Septima — Rulebook (corpus doc 1120) | SPELLS | p.9 | 0.045956 (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 Septima — Rulebook (corpus doc 1120) | HUNTER ROLL | p.10 | 0.045445 (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 Septima — Rulebook (corpus doc 1120) | 5 MOON PHASES · 3x 4x 5 6 A SELECT ACTION · Player board | p.6 | 0.043935 (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 Septima — Rulebook (corpus doc 1120) | PLAYER SETUP | p.5 | 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 |
| #6 | RULEBOOK Septima — Rulebook (corpus doc 1120) | PLAYER SETUP | p.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)) | 300 |
| #7 | RULEBOOK Septima — Rulebook (corpus doc 1120) | SELECT ACTION | p.14 | 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 |
| #8 | RULEBOOK Septima — Rulebook (corpus doc 1120) | PLAYER SETUP · FULL GAME · 6 SEASON SEQUENCE | p.6 | 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)) | 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 67 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 Septima — Rulebook (corpus doc 1120) | RESOLVE ACTION | p.7 | #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 Septima — Rulebook (corpus doc 1120) | PLAYER SETUP FOR SOLO · PREPARATION · MOON PHASES | p.14 | #10 | 0.028958 (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 |
| #3 | RULEBOOK Septima — Rulebook (corpus doc 1120) | RESOLVE ACTION · BLACK WIDOW'S SUSPICION | p.14 | #13 | 0.025795 (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 |
| #4 | RULEBOOK Septima — Rulebook (corpus doc 1120) | 5 MOON PHASES · 3x 4x 5 6 A SELECT ACTION · Player board | p.6 | #4 | 0.043935 (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 Septima — Rulebook (corpus doc 1120) | PLAYER SETUP | p.5 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Septima — Rulebook (corpus doc 1120) | HUNTER ROLL | p.10 | #3 | 0.045445 (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 Septima — Rulebook (corpus doc 1120) | SPELLS | p.9 | #2 | 0.045956 (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 |
| #8 | RULEBOOK Septima — Rulebook (corpus doc 1120) | SPELLS | p.9 | #19 | 0.014493 (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 Septima — Rulebook (corpus doc 1120) | RESOLVE ACTION | p.7 | no quote on the wire |
| [2] | RULEBOOK Septima — Rulebook (corpus doc 1120) | RESOLVE ACTION · BLACK WIDOW'S SUSPICION | p.14 | no quote on the wire |
| [3] | RULEBOOK Septima — Rulebook (corpus doc 1120) | SPELLS | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 85 ms · first delta 3056 ms · total 5404 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 85 ms · ask 5318 ms · gateway work 5404 ms · total 5404 ms
- tokens in (the prompt the answerer read)
- 4573
- tokens out (what the answerer generated)
- 451
- tok/sec
- 200.1 tok/sec — 451 output tokens in 2.254 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 53s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, checked 10s 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 1050), 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.