You asked
What is the correct arrangement of components at the very beginning of a game?
Answered counted as answeredAsked with: Descent: Legends of the Darkbg-322708-en-1e
Before playing for the first time, assemble the plastic figures, health dials, and terrain pieces following the instructions on the Component Assembly insert [1]. To set up a campaign, follow these steps: 1. Launch the Descent: Legends of the Dark app and select “New Game” [2][3]. 2. Use the app to create a save slot, select a difficulty setting, and choose starting characters [2][3]. 3. Gather hero components by taking a reference card, a health dial, the plastic figure and hero card that match the chosen hero, and that hero’s two starting weapon cards [2][3]. 4. Combine starting weapons by placing one weapon on top of the other so the faces with the upgrade (<0xEF><0x97><0xA2>) icon face each other, then insert the pair into a card sleeve [2][3]. 5. Set up a play area in front of each player to place gathered components [2][3]. 6. A hero can begin the game with either side of their hero card and attack card faceup [2][3].
🔧 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 340 ms · ask 11181 ms · total 11532 ms
- single-flight (PR-5)
- queued 0 ms · generation 11532 ms
- retrieval refs (raw)
- [{"page": 7, "score": 0.032787, "snippet": "Set Health Dial: Each player sets their health dial to the number that matches the maximum health value on their hero card. The Elf Huntsman 1 : During your turn, ^«®¥ã ϭ 'My family is gone. Their teachings are not.' Add 1 . Then you may suffer 1 Create Supply: Separate all tokens by type and place ", "headingPath": "seTup", "sharpsignalDocId": 499}, {"page": 32, "score": 0.032258, "snippet": "Learn to Play 32 Quick reFerence rOund sTrucTure Each game round consists of the following two phases: 1. Hero Phase: During this phase, each hero takes a turn performing actions to move, attack enemies, and interact with tokens and terrain. 2. Darkness Phase: During this phase, time passes and enem", "headingPath": "", "sharpsignalDocId": 499}, {"page": 30, "score": 0.031746, "snippet": "Each ability describes when it can be used. Most commonly, abilities can be used 'before,' 'after,' or 'during' a specific time or action of the game, as follows: ◊ If the timing of an ability uses the word 'before' or 'after,' the ability's effect can be resolved immediately before or after the des", "headingPath": "Timing · GOLDEN RULES", "sharpsignalDocId": 499}, {"page": 3, "score": 0.03125, "snippet": "1 Component Assembly Insert 1 Lore Guide 9 Custom Dice 18 Map Tiles 40 Weapon Cards 42 Skill Cards 12 Explore/Sight Tokens 46 Terrain Pieces 18 Armor Cards 10 Injury Cards 80 Condition Tokens (16 of each type) 16 Plastic ID Markers (4 of each color) 6 Underlays 12 Trinket Cards 4 Reference Cards 56 ", "headingPath": "rules sTrucTure · cOmpOnenTs", "sharpsignalDocId": 499}, {"page": 26, "score": 0.030769, "snippet": "The rules presented in this section are not necessary to begin playing the game . When the heroes gain access to the campaign map in the app, they should read the rules presented in this section and continue the campaign. Early in the campaign, the heroes gain access to additional features in the ap", "headingPath": "cAmpAign rules · eQuipmenT", "sharpsignalDocId": 499}, {"page": 8, "score": 0.030303, "snippet": "A single game of Descent: Legends of the Dark represents one quest that is played over a series of rounds, and each round consists of two phases that players resolve in the following order: Hero Phase: During this phase, the heroes can move around the map, attack enemies, and interact with their env", "headingPath": "seTup · herO phAse · mAneuver · Impeded", "sharpsignalDocId": 499}, {"page": 6, "score": 0.029851, "snippet": "To set up a campaign of Descent: Legends of the Dark , follow the steps presented in this section. Launch App: Players launch the Descent: Legends of the Dark app and select 'New Game.' The app guides players through a series of screens to create a save slot, select a difficulty setting, and choose ", "headingPath": "seTup", "sharpsignalDocId": 499}, {"page": 29, "score": 0.029412, "snippet": "Players can save their campaign at any time by selecting 'Save & Quit' from the options menu. If players choose to save their game during a quest, it is important that the heroes record the location of all figures on the map as well as the arrangement of their play areas-this includes the types and ", "headingPath": "sAving A cAmpAign · cOnTinuing A cAmpAign", "sharpsignalDocId": 499}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "BLOOD AND FLAME · Overview · The App · Assembly · rules sTrucTure", "sharpsignalDocId": 499}, {"page": 6, "quote": null, "headingPath": "", "sharpsignalDocId": 499}, {"page": 6, "quote": null, "headingPath": "seTup", "sharpsignalDocId": 499}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 499 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 499 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 7, 2026 06:12
retrieval — what the search arm returned
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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | seTup | p.7 | 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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | p.32 | 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 | |
| #3 | RULEBOOK Descent: Legends of the Dark — Rulebook (corpus doc 499) | Timing · GOLDEN RULES | p.30 | 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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | rules sTrucTure · cOmpOnenTs | p.3 | 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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | cAmpAign rules · eQuipmenT | p.26 | 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 |
| #6 | RULEBOOK Descent: Legends of the Dark — Rulebook (corpus doc 499) | seTup · herO phAse · mAneuver · Impeded | p.8 | 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 |
| #7 | RULEBOOK Descent: Legends of the Dark — Rulebook (corpus doc 499) | seTup | p.6 | 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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | sAving A cAmpAign · cOnTinuing A cAmpAign | p.29 | 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 |
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 Descent: Legends of the Dark — Rulebook (corpus doc 499) | BLOOD AND FLAME · Overview · The App · Assembly · rules sTrucTure | p.2 | no quote on the wire |
| [2] | RULEBOOK Descent: Legends of the Dark — Rulebook (corpus doc 499) | p.6 | no quote on the wire | |
| [3] | RULEBOOK Descent: Legends of the Dark — Rulebook (corpus doc 499) | seTup | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 340 ms · first delta 9909 ms · total 11532 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 340 ms · ask 11181 ms · gateway work 11532 ms · total 11532 ms
- tokens in (the prompt the answerer read)
- 3819
- tokens out (what the answerer generated)
- 230
- tok/sec
- 147.0 tok/sec — 230 output tokens in 1.565 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 57s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- BEGIN — "begin" / "beginning"
- matched words (in the normalized question)
-
beginning
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 430), 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.