You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Nemesis: Retaliationbg-381248-en-1e
Before the game begins, players take and place the following: * Each player is dealt one Help card [1]. * Each player is dealt 1 random Private Objective card and 1 random Mission Objective card face down [1]. * Each player draws 5 Action cards to their hand from their Action deck [2][3]. * The player with the highest player number chooses 1 Support Equipment card (from a revealed pool of 7) and places it in their player area [3]. * Each other player chooses 1 Support Equipment card until all players have one [3]. * If any chosen Equipment has empty Tactical Gear slots, they are filled with appropriate Tactical Gear tokens from the insert [3]. * Each player chooses 4 Tactical Gear tokens of their choice and places them in their Tactical Belt on the left side of their Character board [3]. * One random Mission Task card is drawn and placed face up on the Mission Task slot on the bottom Round track tile [1].
🔧 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 337 ms · ask 17571 ms · total 17920 ms
- single-flight (PR-5)
- queued 0 ms · generation 17920 ms
- retrieval refs (raw)
- [{"page": 10, "score": 0.032787, "snippet": "This choice can be done simultaneously, but if necessary perform it in de- scending player number order. Note: For/uni00A0the/uni00A0first game we recommend starting with 1 to- ken of each type. beginning of the game 1. Each player draws 5 Action cards to/uni00A0 their hand from their Action deck. 2.", "headingPath": "", "sharpsignalDocId": 378}, {"page": 12, "score": 0.032258, "snippet": "TURN ORDER AS TIEBREAKER Turn order is the/uni00A0most common way to/uni00A0break ties in Nemesis . The Rulebook may call out the/uni00A0Character first in Turn order. In any such case it describes the Starting player (the player that currently holds the Starting Player token) or is closest to/uni00A", "headingPath": "", "sharpsignalDocId": 378}, {"page": 12, "score": 0.031746, "snippet": "12 players' turns During their Turn a player must resolve the/uni00A03 following steps in order: 1. Perform 2 Actions 2. Oxygen Loss 3. Fire Damage Players may also, once per game, choose an/uni00A0Objective during their Turn/uni00A0– this does not count as an/uni00A0Action. More about Choosing an O", "headingPath": "", "sharpsignalDocId": 378}, {"page": 12, "score": 0.03125, "snippet": "Oxygen Loss /uni00A0– If you are in a Section with Inactive Life Sup - port Systems ( ) lose 1 Oxygen ( ) lose 1 Oxygen ( ). 3. Fire Damage /uni00A0– If you are in a Room with Fire ( ) lose 1/uni00A0Health Point ( ). This process repeats until all players have Passed. INTRUDER PHASE 1. Intruders Bur", "headingPath": "", "sharpsignalDocId": 378}, {"page": 13, "score": 0.030769, "snippet": "Reactions are not Actions and/uni00A0do not count toward/uni00A0the/uni00A0Actions per Turn limit. choosing an objective During their Turns, players may also choose their Objective. Each player may only choose an/uni00A0Objective once per game, while they still have 2 Objective cards. An/uni00A0Obje", "headingPath": "", "sharpsignalDocId": 378}, {"page": 10, "score": 0.030303, "snippet": "10 player setup objective setup and character draft To setup the/uni00A0players, perform the/uni00A0following: 1. Find Help cards with numbers corresponding to/uni00A0the/uni00A0number of players taking part in the/uni00A0game (e.g./uni00A0if there are 3 players in the/uni00A0game, find cards “1”, “2", "headingPath": "", "sharpsignalDocId": 378}, {"page": 26, "score": 0.029851, "snippet": "The player performs a “Make a Move” Action. They discard a card from their hand to pay the Action’s cost. Then, they: 1. Choose Direction /uni00A0– They choose the upper Corridor to move through (they could also choose the middle or the lower one). 2. Resolve Opportunity Attacks /uni00A0– Since ther", "headingPath": "", "sharpsignalDocId": 378}, {"page": 12, "score": 0.029412, "snippet": "To perform an/uni00A0Action, the/uni00A0player pays a cost listed above by discard- ing an/uni00A0appropriate number of Action cards from hand to their discard pile, face up. Then, they resolve the/uni00A0chosen Action. Note that in Nemesis Pass is an Action. A player does not Pass automatically whe", "headingPath": "", "sharpsignalDocId": 378}]
- citations (raw)
- [{"page": 10, "quote": null, "headingPath": "", "sharpsignalDocId": 378}, {"page": 10, "quote": null, "headingPath": "", "sharpsignalDocId": 378}, {"page": 10, "quote": null, "headingPath": "", "sharpsignalDocId": 378}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 378 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 378 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 18:25
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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.10 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.12 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.12 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.12 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.13 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.26 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.12 | 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 Nemesis: Retaliation — Rulebook (corpus doc 378) | p.10 | no quote on the wire | |
| [2] | RULEBOOK Nemesis: Retaliation — Rulebook (corpus doc 378) | p.10 | no quote on the wire | |
| [3] | RULEBOOK Nemesis: Retaliation — Rulebook (corpus doc 378) | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 337 ms · first delta 16289 ms · total 17920 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 337 ms · ask 17571 ms · gateway work 17920 ms · total 17920 ms
- tokens in (the prompt the answerer read)
- 4154
- tokens out (what the answerer generated)
- 216
- tok/sec
- 136.9 tok/sec — 216 output tokens in 1.578 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s 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)
-
begin
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 307), 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.