You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Star Wars: Armadabg-163745-en-1e
1. Clear a 3' x 6' play area [1]. 2. Establish a 3' x 4' setup area by using the length of the range ruler to place the setup area markers 1' from the short edges of the play area (if playing with only ships and squadrons in the core set, use a 3' x 3' play area that also functions as the setup area) [1]. 3. Players sit across from each other on the 6' edges of the play area [1]. 4. Each player places his ships, squadrons, and cards next to the play area and near his edge [1]. 5. Set each shield dial and squadron disk to its maximum shield and hull values [1]. 6. Set the activation slider of each squadron to display the blue end of the slider with the icon [1]. 7. Assign appropriate defense tokens to each ship and unique squadron [1]. 8. Gather enough command dials and speed dials for the fleet [1]. 9. Assign ID tokens to ships and squadrons as necessary [1]. 10. The player whose fleet has the lowest total fleet point cost chooses which player is the first player; if tied, players flip a coin to decide [1]. 11. The first player places the initiative token next to his edge with the icon side faceup [1]. 12. The first player looks at all three of his opponent's objectives cards and chooses one to be the objective for the game [1]. 13. Starting with the second player, players take turns choosing and placing six obstacles into the play area (if playing with only ships and squadrons included in the box, players place only four obstacles) [1]. Obstacles must be placed within the setup area, beyond distance 3 of the edges of the play area, and beyond distance 1 of each other [1]. 14. Starting with the first player, players take turns deploying forces into the setup area [1]. A single deployment turn consists of placing one ship or two squadrons [1]. Ships must be placed within their player's deployment zone (the portion of the setup area at distance 1-3 of his edge) [1]. When a player places a ship, he must set its speed dial to a speed available on its speed chart [1]. Squadrons must be placed within distance 1-2 of a friendly ship [2]. 15. After placing obstacles, players alternate placing a total of 5 objective tokens in the setup area, starting with the second player [3][4]. Each token must be placed beyond distance 5 of both players' edges and beyond distance 3 of all other objective tokens [3][4]. 16. After deploying fleets, each player chooses one of his ships to be an objective ship, starting with the first player [3]. 17. Shuffle the damage deck and place it next to the play area along with the command tokens, maneuver tool, range ruler, and the round token marked '1' [2]. 18. Remove the setup area markers from the play area [2].
🔧 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 293 ms · ask 14131 ms · total 14437 ms
- single-flight (PR-5)
- queued 0 ms · generation 14437 ms
- retrieval refs (raw)
- [{"page": 23, "score": 0.032787, "snippet": "A single deployment turn consists of placing one ship or two squadrons. Ships must be placed within their player's deployment zone. A player's deployment zone is the portion of the setup area that is at distance 1-3 of his edge of the play area. When a player places a ship, he must set its speed dia", "headingPath": "COMPLETE SETUP", "sharpsignalDocId": 513}, {"page": 23, "score": 0.032258, "snippet": "Once players are comfortable with the rules of the game, they should use the complete setup rules. To do so, proceed through the following steps in order (see the 'Complete Setup' diagram on page 24). 1 . Define Play Area & Setup Area: Clear a 3' x 6' play area. Then, establish a 3' x 4' setup area ", "headingPath": "COMPLETE SETUP", "sharpsignalDocId": 513}, {"page": 21, "score": 0.031746, "snippet": "Many upgrade card effects have a specific time during the game when they occur, which is described on the card. Some cards use a header to indicate when the card can be used as described below: Effects that modify attack dice, such as by adding, changing, or rerolling dice, may be resolved after the", "headingPath": "Using Upgrade Cards · Scoring Upgrade Cards", "sharpsignalDocId": 513}, {"page": 9, "score": 0.03125, "snippet": "(see 'Determine Course Example' on the right). Each column on the speed chart corresponds to the speed number at the bottom of the column. A column shows the number of times that each joint can be clicked while going at that speed. Each row corresponds to one of the joints on the maneuver tool; the ", "headingPath": "Determine Course", "sharpsignalDocId": 513}, {"page": 7, "score": 0.030769, "snippet": "During this phase, players secretly and simultaneously use their command dials to choose commands for each of their ships. When revealed, each command provides that ship with a powerful bonus. To choose a command, rotate the command dial so that the desired command icon is framed by the dial's faste", "headingPath": "PHASE 1: COMMAND PHASE", "sharpsignalDocId": 513}, {"page": 10, "score": 0.030303, "snippet": "The player places the maneuver tool on one side of his ship so that the plastic guides of the tool's flat end slide into the notches on the side of the ship's base. If properly inserted, the front of the ship should be parallel with the raised line above the guides. The player presses the maneuver t", "headingPath": "Move Ship · PHASE 3: SQUADRON PHASE · sqUadron movement", "sharpsignalDocId": 513}, {"page": 8, "score": 0.029851, "snippet": "During this step, the ship can perform up to two attacks. An attack originates from one hull zone , and the target must be inside that hull zone's firing arc (see 'Firing Arcs and Hull Zones' on page 9). The target of the attack can be either one hull zone of an enemy ship or one or more enemy squad", "headingPath": "attack · execUte maneUver · Determine Course", "sharpsignalDocId": 513}, {"page": 9, "score": 0.029412, "snippet": "9 (see “Determine Course Example” on the right). Each column on the speed chart corresponds to the speed number at the bottom of the column. A column shows the number of times that each joint can be clicked while going at that speed. Each row corresponds to one of the joints on the maneuver tool; th", "headingPath": "", "sharpsignalDocId": 513}]
- citations (raw)
- [{"page": 23, "quote": null, "headingPath": "COMPLETE SETUP", "sharpsignalDocId": 513}, {"page": 23, "quote": null, "headingPath": "COMPLETE SETUP", "sharpsignalDocId": 513}, {"page": 22, "quote": null, "headingPath": "OBJECTIVES", "sharpsignalDocId": 513}, {"page": 3, "quote": null, "headingPath": "", "sharpsignalDocId": 513}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 513 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 513 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 06:01
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 Star Wars: Armada — Rulebook (corpus doc 513) | COMPLETE SETUP | p.23 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | COMPLETE SETUP | p.23 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | Using Upgrade Cards · Scoring Upgrade Cards | p.21 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | Determine Course | p.9 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | PHASE 1: COMMAND PHASE | p.7 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | Move Ship · PHASE 3: SQUADRON PHASE · sqUadron movement | p.10 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | attack · execUte maneUver · Determine Course | p.8 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | p.9 | 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 Star Wars: Armada — Rulebook (corpus doc 513) | COMPLETE SETUP | p.23 | no quote on the wire |
| [2] | RULEBOOK Star Wars: Armada — Rulebook (corpus doc 513) | COMPLETE SETUP | p.23 | no quote on the wire |
| [3] | RULEBOOK Star Wars: Armada — Rulebook (corpus doc 513) | OBJECTIVES | p.22 | no quote on the wire |
| [4] | RULEBOOK Star Wars: Armada — Rulebook (corpus doc 513) | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 293 ms · first delta 9941 ms · total 14437 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 293 ms · ask 14131 ms · gateway work 14437 ms · total 14437 ms
- tokens in (the prompt the answerer read)
- 3899
- tokens out (what the answerer generated)
- 654
- tok/sec
- 147.1 tok/sec — 654 output tokens in 4.445 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 51s 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 444), 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.