You asked
How do I set up the game?
Answered counted as answeredAsked with: Star Wars: Rebellionbg-187645-en-1e
🔧 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 455 ms · ask 15594 ms · total 569751 ms
- single-flight (PR-5)
- queued 553681 ms · generation 16070 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 15, "score": 0.048916, "snippet": "This section of the Rules Reference contains the complete rules for setting up a game of Star Wars: Rebellion . These rules include the advanced rules found in the back of the Learn to Play booklet. After players have played their first game, they should follow the setup rules on this page for all f", "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 15, "score": 0.048131, "snippet": "-Team Game: The Admiral decides where to place starting units. III The Rebel player receives 1 Corellian Corvette, 1 Rebel Transport, 2 X-wings, 2 Y-wings, 6 Rebel T roopers, and 2 Airspeeders. He can place these units on the 'Rebel Base' space and/or any one Rebel or neutral system. -Team Game: The", "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 15, "score": 0.046898, "snippet": "Then the Rebel player draws one objective card. Team Game: The Rebel General draws the objective card. 5 . Prepare Action Decks: Each player takes all of his action cards that have a recruit icon and shuffles them to create his action deck. He places the deck facedown next to his faction sheet on th", "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 4, "score": 0.03125, "snippet": "When a player moves units to a system that contains his opponent's units, a combat is resolved. Combat is only resolved if both players have units in the same theater. 1 . Add Leader: If a player does not have a leader with tactic values in the system, he may take one leader from his leader pool and", "headingPath": "COMBAT", "sharpsignalDocId": 256}, {"page": 12, "score": 0.030769, "snippet": "He takes these units from the supply and places them on his build queue, in the space matching the number to the left of the resource icon. -Team Game: Only each team's Admiral builds new units during this step. 6 . Deploy Units: Starting with the Rebel player, each player slides all units one space", "headingPath": "REFRESH PHASE", "sharpsignalDocId": 256}, {"page": 2, "score": 0.030303, "snippet": "Activating a system using a leader is how players move their units and initiate combat during the Command Phase. T o activate a system, follow these steps: 1 . Place Leader: The player takes a leader from his leader pool and places it in any system. A leader that does not have tactic values cannot a", "headingPath": "ACTIVATING SYSTEMS", "sharpsignalDocId": 256}, {"page": 2, "score": 0.029907, "snippet": "This document is intended as a reference for all rules queries. It is recommended that players begin playing Star Wars: Rebellion by reading the Learn to Play booklet in its entirety fi rst . Then, as questions arise during gameplay, players refer to this reference. The majority of this reference is", "headingPath": "USING THIS REFERENCE · GLOSSARY", "sharpsignalDocId": 256}, {"page": 12, "score": 0.029851, "snippet": "During the Refresh Phase, players perform cleanup steps in preparation for the next game round: 1 . Retrieve Leaders: Players return all their leaders from the game board to their leader pools. If a leader is still on a mission card, it returns to the leader pool, and the card returns to its owner's", "headingPath": "REFRESH PHASE", "sharpsignalDocId": 256}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 15, "quote": null, "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 15, "quote": null, "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 15, "quote": null, "headingPath": "APPENDIX: COMPLETE SETUP", "sharpsignalDocId": 256}, {"page": 2, "quote": null, "headingPath": "ACTION CARDS", "sharpsignalDocId": 256}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 256 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 256 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 6, 2026 14:17
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. How much wider that pool was is set gateway-side and is NOT REPORTED for this ruling, and neither are the answerer's final rows — so rulesage has nothing of its own to show beside these.
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: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | 0.048916 (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: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | 0.048131 (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: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | 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 Star Wars: Rebellion — Rulebook (corpus doc 256) | COMBAT | p.4 | 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: Rebellion — Rulebook (corpus doc 256) | REFRESH PHASE | p.12 | 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: Rebellion — Rulebook (corpus doc 256) | ACTIVATING SYSTEMS | p.2 | 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: Rebellion — Rulebook (corpus doc 256) | USING THIS REFERENCE · GLOSSARY | p.2 | 0.029907 (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: Rebellion — Rulebook (corpus doc 256) | REFRESH PHASE | p.12 | 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.
the passages the answerer read: NOT RECORDED for this ruling. Any of three things leaves this empty, and they are all different from the answerer having had nothing to read: this ask may never have reached a gateway at all; a multi-book ask keeps each book's own context on that book's own page rather than here; or the gateway build that answered may simply not report it. What this NEVER means is that the answerer read nothing — an answer was composed from passages either way, and their absence here is a gap in what we were told, not in what it read.
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: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | no quote on the wire |
| [2] | RULEBOOK Star Wars: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | no quote on the wire |
| [3] | RULEBOOK Star Wars: Rebellion — Rulebook (corpus doc 256) | APPENDIX: COMPLETE SETUP | p.15 | no quote on the wire |
| [4] | RULEBOOK Star Wars: Rebellion — Rulebook (corpus doc 256) | ACTION CARDS | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 455 ms · first delta 8471 ms · total 569751 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 553681 ms · retrieval 455 ms · ask 15594 ms · gateway work 16070 ms · total 569751 ms
- tokens in (the prompt the answerer read)
- 3800
- tokens out (what the answerer generated)
- 1020
- tok/sec
- 135.4 tok/sec — 1020 output tokens in 7.536 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 27s 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
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 181), 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.