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. 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)

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.

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 9861 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 9861 ms · total 9861 ms

live seat (read from the running child)

answering — gemma4:26b think:false · num_ctx 32768 (live-verified 8s 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

REFUSED_UNVERIFIED — Refused — answer could not be verified against the rulebook

abstain rationale

withheld BY DESIGN: this refusal's text is the drafted answer that failed the quote gate, and nothing unverified serves (D-9) — it is never recorded, here or anywhere a reader can reach

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

layers — one row per book this ask read

#	book	outcome	timings	search refs	answer cited	stream	arms	row
1	Carcassonne (bg-822-en-1e)	Answered	queued 0 ms · search 378 ms · ask 4041 ms · first delta 3272 ms · gateway work 4435 ms	8	1	STREAMED	base rulebook doc 123 boosted · no registered errata card matched · keyed on edition 45	ruling 1466
2	Carcassonne: Inns & Cathedrals (bg-4956-en-1e)	Answered	queued 0 ms · search 323 ms · ask 2097 ms · first delta 1986 ms · gateway work 2426 ms	4	2	STREAMED	no base-rulebook boost — this edition registers no ingested rulebook to anchor retrieval to · no registered errata card matched · keyed on edition 116	ruling 1467
3	Carcassonne: Traders & Builders (bg-5405-en-1e)	Answered	queued 0 ms · search 239 ms · ask 2753 ms · first delta 2218 ms · gateway work 3000 ms	6	3	STREAMED	no base-rulebook boost — this edition registers no ingested rulebook to anchor retrieval to · no registered errata card matched · keyed on edition 117	ruling 1468

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 45), 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.