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 Citadels — Rulebook (corpus doc 137)	setup · playInG the GaMe	p.3	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Citadels — Rulebook (corpus doc 137)	custoMIzatIon rules · usInG 9 characters · coMplete setup	p.8	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 Citadels — Rulebook (corpus doc 137)	your fIrst GaMe	p.2	0.047875 (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 Citadels — Rulebook (corpus doc 137)	playInG wIth 2-3 players · setup · seleCtion phase · Game enD · GeM shapes on cards	p.7	0.046875 (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 Citadels — Rulebook (corpus doc 137)	character abIlItIes In detaIl	p.10	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 Citadels — Rulebook (corpus doc 137)	turn phase · DistriCts	p.4	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 Citadels — Rulebook (corpus doc 137)	character abIlItIes In detaIl	p.10	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 Citadels — Rulebook (corpus doc 137)	character abIlItIes In detaIl	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 Citadels — Rulebook (corpus doc 137)	setup · playInG the GaMe	p.3	no quote on the wire

generation — timing and the path taken

timing split

retrieval 298 ms · first delta 6427 ms · total 1855966 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)

full breakdown

queued 1848200 ms · retrieval 298 ms · ask 7459 ms · gateway work 7766 ms · total 1855966 ms

tokens in (the prompt the answerer read)

3268

tokens out (what the answerer generated)

178

tok/sec

137.6 tok/sec — 178 output tokens in 1.294 s of generation

live seat (read from the running child)

answering — gemma4:26b think:false · num_ctx 32768 (live-verified 59s 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 59), 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.