retrieval — what the search arm returned

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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.

no payload was recorded for this ruling (the call never returned one)

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.

no payload was recorded for this ruling (the call never returned one)

generation — timing and the path taken

timing split

retrieval n/a · first delta n/a · total 23299 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 n/a ms · ask n/a ms · gateway work 23299 ms · total 23299 ms

live seat (read from the running child)

answering — gemma4:26b think:false · num_ctx 32768 (live-verified 54s ago)

stream path

not requested — no progress token attached (stream-answers off, or a non-streaming caller)

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

the answerer offered no rationale text with this refusal (or the ruling predates the abstain_rationale column, V41)

setup-shape — why the checklist band did or didn't render

decision

NOT_SETUP_SHAPED — no setup-shape pattern matched this question

layers — one row per book this ask read

#	book	outcome	timings	refs	cited	stream	arms	row
probe	every book, read together (bg-162886-en-1e)	Abstained — no grounded answer; closest passages below	queued 0 ms · search 239 ms · ask 8398 ms · first delta 8525 ms · gateway work 8646 ms	8	0	STREAMED	base rulebook doc 58 boosted · no registered errata card matched · keyed on edition 7	ruling 1559
1	Spirit Island (bg-162886-en-1e)	Abstained — no grounded answer; closest passages below	queued 0 ms · search 272 ms · ask 7811 ms · first delta 7989 ms · gateway work 8092 ms	8	0	STREAMED	base rulebook doc 58 boosted · no registered errata card matched · keyed on edition 7	ruling 1560
2	Spirit Island: Branch & Claw (bg-191831-en-1e)	Abstained — no grounded answer; closest passages below	queued 0 ms · search 263 ms · ask 6289 ms · first delta 6431 ms · gateway work 6561 ms	8	0	STREAMED	no base-rulebook boost — this edition registers no ingested rulebook to anchor retrieval to · no registered errata card matched · keyed on edition 122	ruling 1561

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 7), so "no registered errata card matched" above could never have matched one

Errata scope: each book this ask READ got its own errata gate, keyed on that book's own edition — so an expansion's registered cards were matched against that expansion's own layer rather than left outside the match. The per-layer table above shows what each one sent, and any book that was not read ran no gate at all.