You asked
How do I setup the game?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Coupbg-131357-en-1e
Answered before
This question didn't get an answer just now — but Coup has been asked something like it before. The corpus may have changed since, so check the date and the answerer on each one before you rule from it.
The answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.
In the not too distant future, the government is run for profit by a new 'royal class' of multinational CEOs. Their greed and absolute control of the economy has reduced all but a privileged few to lives of poverty and desperation. Out of the oppressed masses rose The Resistance, an underground orga
Your local hobby store has the Reformation expansion that brings more roles, more actions and more players to Coup. If you enjoy Coup, look for other games in at your local hobby store. is the ultimate game of hidden identities, deduction and deception for 5 to 10 players. Hidden Agenda and Hostile
To eliminate the influence of all other players and be the last survivor. Face down cards in front of a player represent who they influence at court. The characters printed on their face down cards represents which characters that player influences and their abilities. Every time a player loses an i
A player may choose any action they want and can afford. Some actions (Character Actions) require influencing characters. If they choose a Character Action a player must claim that the required character is one of their face down cards. They can be telling the truth or bluffing. They do not need to
Natasha has 2 influence remaining (Contessa and Duke) and 1 coin. Sacha has 1 influence remaining (Captain) and 5 coins. Haig is out of the game. Two Assassins and One Contessa have been revealed and are face up on the table. It is possible to lose 2 influence in one turn if you unsuccessfully defen
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 491 ms · ask 2986 ms · total 3498 ms
- single-flight (PR-5)
- queued 0 ms · generation 3498 ms
- retrieval refs (raw)
- [{"page": 1, "score": 0.048916, "snippet": "In the not too distant future, the government is run for profit by a new 'royal class' of multinational CEOs. Their greed and absolute control of the economy has reduced all but a privileged few to lives of poverty and desperation. Out of the oppressed masses rose The Resistance, an underground orga", "headingPath": "Contents · Set-Up", "sharpsignalDocId": 180}, {"page": 8, "score": 0.032258, "snippet": "Your local hobby store has the Reformation expansion that brings more roles, more actions and more players to Coup. If you enjoy Coup, look for other games in at your local hobby store. is the ultimate game of hidden identities, deduction and deception for 5 to 10 players. Hidden Agenda and Hostile ", "headingPath": "Like Coup? · The Resistance Universe · The Resistance", "sharpsignalDocId": 180}, {"page": 2, "score": 0.031746, "snippet": "To eliminate the influence of all other players and be the last survivor. Face down cards in front of a player represent who they influence at court. The characters printed on their face down cards represents which characters that player influences and their abilities. Every time a player loses an i", "headingPath": "Goal · Influence · Game Play", "sharpsignalDocId": 180}, {"page": 3, "score": 0.03125, "snippet": "A player may choose any action they want and can afford. Some actions (Character Actions) require influencing characters. If they choose a Character Action a player must claim that the required character is one of their face down cards. They can be telling the truth or bluffing. They do not need to ", "headingPath": "Actions · General Actions · Income · Foreign Aid · Coup · Character Actions · …", "sharpsignalDocId": 180}, {"page": 7, "score": 0.030886, "snippet": "Natasha has 2 influence remaining (Contessa and Duke) and 1 coin. Sacha has 1 influence remaining (Captain) and 5 coins. Haig is out of the game. Two Assassins and One Contessa have been revealed and are face up on the table. It is possible to lose 2 influence in one turn if you unsuccessfully defen", "headingPath": "At this stage · Note: Double Dangers of Assasination · Total (Lack of) Trust · Two Player Coup & Two Player Variant · As a variant, Coup can be played with two players with these changes to the setup: · Credits", "sharpsignalDocId": 180}, {"page": 5, "score": 0.030769, "snippet": "If a player wins a challenge by showing the relevant character card, they first return that card to the Court deck, re-shuffle the Court deck and take a random replacement card. (That way they have not lost an influence and other players do not know the new influence card they have). Then the action", "headingPath": "", "sharpsignalDocId": 180}, {"page": 5, "score": 0.030303, "snippet": "Captain – Steal Take 2 coins from another player. If they only have one coin, take only one. (Can be blocked by the Ambassador or the Captain) Ambassador – Exchange Exchange cards with the Court. First take 2 random cards from the Court deck. Choose which, if any, to exchange with your face down car", "headingPath": "", "sharpsignalDocId": 180}, {"page": 6, "score": 0.029851, "snippet": "Haig has been dealt an Assassin and a Duke. On his first turn he claims the Duke and takes 3 coins. Sacha thinks Haig is bluffing and challenges him. Haig shows a Duke and wins the challenge. Haig keeps the 3 coins that the Duke provided him but has to return his Duke card to the Court. He shuffles ", "headingPath": "3 players. Each start with 2 influence cards and 2 coins. The remaining 9 character cards make up the Court deck. · After the first turn: · Continuing on...", "sharpsignalDocId": 180}]
- citations (raw)
- []
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 180 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 180 boosted
- answered-before recall
-
past answered rulings were found and offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- ruling 2094 — matched by trigram similarity — measured similarity 0.8148
- debug row retained until
- Nov 3, 2026 13:28
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 Coup — Rulebook (corpus doc 180) | Contents · Set-Up | p.1 | 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 Coup — Rulebook (corpus doc 180) | Like Coup? · The Resistance Universe · The Resistance | p.8 | 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 Coup — Rulebook (corpus doc 180) | Goal · Influence · Game Play | p.2 | 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 Coup — Rulebook (corpus doc 180) | Actions · General Actions · Income · Foreign Aid · Coup · Character Actions · … | 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 Coup — Rulebook (corpus doc 180) | At this stage · Note: Double Dangers of Assasination · Total (Lack of) Trust · Two Player Coup & Two Player Variant · As a variant, Coup can be played with two players with these changes to the setup: · Credits | p.7 | 0.030886 (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 Coup — Rulebook (corpus doc 180) | 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 Coup — Rulebook (corpus doc 180) | p.5 | 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 Coup — Rulebook (corpus doc 180) | 3 players. Each start with 2 influence cards and 2 coins. The remaining 9 character cards make up the Court deck. · After the first turn: · Continuing on... | 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 |
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 |
|---|
generation — timing and the path taken
- timing split
- retrieval 491 ms · first delta 3395 ms · total 3498 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 491 ms · ask 2986 ms · gateway work 3498 ms · total 3498 ms
- tokens in (the prompt the answerer read)
- 3066
- tokens out (what the answerer generated)
- 9
- tok/sec
- 128.6 tok/sec — 9 output tokens in 0.070 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
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
-
I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped
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)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 98), 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.