You asked
What happens when the barbarians attack?
Abstained — no grounded answer; closest passages below counted as honest abstain 0 of 2 books answeredAsked with: 7 Wonders (2nd Edition)bg-316377-en-2e · 7 Wonders: Leadersbg-291204-en-1e
Read together first; no grounded answer, so each book was read on its own.
7 Wonders (2nd Edition)bg-316377-en-2e Abstained — no grounded answer; closest passages below
The answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.
Each Age ends with the Resolution of Military Conflicts. Count all military symbols on cards you have constructed and those on your Wonder board, if any, to determine your military strength . Then compare your total military strength with that of each of your neighbors. For each neighbor: If your mi
Military Conflict tokens represent your Military Victories and Defeats. There are four types of Military Conflict tokens: Military Defeat -1 tokens Military Victory +1 tokens Military Victory +3 tokens Military Victory +5 tokens
Add the value of all your Military Defeat and Victory tokens to determine your score for Military Conflicts (the total may be a negative number).
If your City does not produce the resources needed to construct a card or Wonder stage, check your neighbors' Cities. If they produce the resources you need, you can buy these resources from them. For each resource bought, give 2 Coins to the owner of the resource. This player keeps their card and c
To buy resources, you must spend the required Coins at the beginning of your turn. You cannot use Coins you receive from other players during the same turn. You cannot buy resources from a Building your neighbor constructed that same turn. You can never prevent a player from buying your resources. B
The answerer's own words:
I don't have enough information.
7 Wonders: Leadersbg-291204-en-1e Abstained — no grounded answer; closest passages below
7 Wonders: Leaders has nothing to add here — an expansion's rulebook only speaks where it changes the game, so silence on a base-game question is the book working, not failing.
The answerer's own words:
I don't have enough information.
Strategy guides → — community tips, kept separate from rulings
🔧 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 null ms · ask null ms · total 11820 ms
- single-flight (PR-5)
- queued 0 ms · generation 11820 ms
- retrieval refs (raw)
- citations (raw)
- boost provenance — errata + base rulebook (E2/E3)
- gate not evaluated for this ruling (boost, supersedence, and wrench all off at ask time), and the base-rulebook arm went unrecorded for the same reason — the wrench that would have stored it was off; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
- layering — route
- layered — the books were read together first and that read did not answer, so each book was then read on its own
- layering — how this ask was counted
- counted as ABSTAINED — carried by layer 1 (7 Wonders (2nd Edition)); layer 2 ABSTAINED; 0 not read; rung: ANSWERED ▸ ABSTAINED ▸ UNATTRIBUTABLE ▸ REFUSED
- layering — books not run
- layer valve: rulesage.table.max-layers = 8 (today's setting, not necessarily the one this ask ran under). A book the valve trims is not read and leaves NO row of its own, so it cannot be listed above or counted in the census — an empty list here means the corpus breaker marked nobody, not that nothing was left out.
- layering — the pooled probe
- ABSTAINED — queued 0 ms · search 270 ms · ask 4772 ms · first delta 4947 ms · gateway work 5051 ms · refs 8
- layering — queued between books
- queued between layers: 0 ms of the 0 ms total queue wait (every wait after the first is a mid-ask wait, because the generation permit is released and re-taken for each book)
- answered-before recall
-
no past answered ruling for this game matched closely enough
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 3, 2026 20:51
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 11820 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 11820 ms · total 11820 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 37s 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-316377-en-2e) | Abstained — no grounded answer; closest passages below | queued 0 ms · search 270 ms · ask 4772 ms · first delta 4947 ms · gateway work 5051 ms | 8 | 0 | STREAMED | base rulebook doc 67 boosted · no registered errata card matched · keyed on edition 12 | ruling 1588 |
| 1 | 7 Wonders (2nd Edition) (bg-316377-en-2e) | Abstained — no grounded answer; closest passages below | queued 0 ms · search 276 ms · ask 4619 ms · first delta 4793 ms · gateway work 4904 ms | 8 | 0 | STREAMED | base rulebook doc 67 boosted · no registered errata card matched · keyed on edition 12 | ruling 1589 |
| 2 | 7 Wonders: Leaders (bg-291204-en-1e) | Abstained — no grounded answer; closest passages below | queued 0 ms · search 232 ms · ask 1627 ms · first delta 1735 ms · gateway work 1865 ms | 4 | 0 | STREAMED | no base-rulebook boost — this edition registers no ingested rulebook to anchor retrieval to · no registered errata card matched · keyed on edition 120 | ruling 1590 |
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 12), 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.